A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on Mechanistic Interpretability, a growing subfield in machine learning interpretability research that aims to reverse-engineer neural networks into understandable computational components.
See the codeREADME
Awesome Mechanistic Interpretability
A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on Mechanistic Interpretability, a growing subfield in machine learning interpretability research that aims to reverse-engineer neural networks into understandable computational components. This repository serves as a comprehensive and well-organized knowledge base for researchers, engineers, and enthusiasts working to uncover the inner workings of modern AI systems, particularly large language models (LLMs).
To ensure that the community stays updated on the latest developments, our repository is automatically updated with recent mechanistic interpretability papers from arXiv. This ensures timely access to new techniques, discoveries, and frameworks that are shaping the future of model transparency and alignment.
[!NOTE] 📢 Announcement: Our paper from AIT Lab is now available on ACM CSUR!
Title: Bridging the Black Box: A Survey on Mechanistic Interpretability in AI
If you find this paper interesting, please consider citing our work. Thank you for your support!
@article{somvanshi2025bridging,
title={Bridging the Black Box: A Survey on Mechanistic Interpretability in AI},
author={Somvanshi, Shriyank and Islam, Md Monzurul and Rafe, Amir and Tusti, Anannya Ghosh and Chakraborty, Arka and Baitullah, Anika and Chowdhury, Tausif Islam and Alnawmasi, Nawaf and Dutta, Anandi and Das, Subasish},
journal={Available at SSRN 5345552},
year={2025}
}
Whether you are investigating the circuits behind in-context learning, decoding attention heads in transformers, or exploring interpretability tools like activation patching and causal tracing, this collection serves as a centralized hub for everything related to Mechanistic Interpretability — enriched by original peer-reviewed contributions and hands-on research from the broader interpretability community.
Updates
- [Feb 04, 2026]: Our paper has been accepted at ACM Computing Surveys 🎉!
- [Jul 24, 2025]: Preprint is now available in SSRN.
Last Updated
September 23, 2026 at 02:55:26 AM UTC
Theorem
Papers (1210)
- Mechanistic Decomposition of Sentence Representations
- Domain Switching on the Pareto Front: Multi-Objective Deep Kernel Learning in Automated Piezoresponse Force Microscopy
- Rethinking Crowd-Sourced Evaluation of Neuron Explanations
- MIB: A Mechanistic Interpretability Benchmark
- Training Superior Sparse Autoencoders for Instruct Models
- RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs
- Performance Gap in Entity Knowledge Extraction Across Modalities in Vision Language Models
- A CRISP approach to QSP: XAI enabling fit-for-purpose models
- Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws
- Tug-of-war between idiom's figurative and literal meanings in LLMs
- TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research
- Evaluating Neuron Explanations: A Unified Framework with Sanity Checks
- A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
- Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective
- The Vector Grounding Problem
- An analytic theory of creativity in convolutional diffusion models
- Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey
- Visualizing and Controlling Cortical Responses Using Voxel-Weighted Activation Maximization
- Is the end of Insight in Sight ?
- Forecasting Seasonal Influenza Epidemics with Physics-Informed Neural Networks
- Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models
- Tracking the Feature Dynamics in LLM Training: A Mechanistic Study
- Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video
- Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning
- Do Large Language Models (Really) Need Statistical Foundations?
- Identifying interactions across brain areas while accounting for individual-neuron dynamics with a Transformer-based variational autoencoder
- SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs
- Anchored Answers: Unravelling Positional Bias in GPT-2's Multiple-Choice Questions
- : Interpreting and leveraging semantic information in diffusion models
- Circuit Stability Characterizes Language Model Generalization
- Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs
- Planning in a recurrent neural network that plays Sokoban
- Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability
- BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model
- Enhancing Automated Interpretability with Output-Centric Feature Descriptions
- Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks
- Sparsification and Reconstruction from the Perspective of Representation Geometry
- Mitigating Overthinking in Large Reasoning Models via Manifold Steering
- Understanding Synthetic Context Extension via Retrieval Heads
- In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention
- MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation
- The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
- Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
- From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance
- Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks
- MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding
- The Birth of Knowledge: Emergent Features across Time, Space, and Scale in Large Language Models
- DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding Spaces
- Multi-Scale Probabilistic Generation Theory: A Hierarchical Framework for Interpreting Large Language Models
- The Origins of Representation Manifolds in Large Language Models
- The Remarkable Robustness of LLMs: Stages of Inference?
- Monet: Mixture of Monosemantic Experts for Transformers
- Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization
- PAL: Probing Audio Encoders via LLMs -- A Study of Information Transfer from Audio Encoders to LLMs
- Revisiting Transformers with Insights from Image Filtering
- Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
- Understanding the Repeat Curse in Large Language Models from a Feature Perspective
- Sectoral Coupling in Linguistic State Space
- SAE-V: Interpreting Multimodal Models for Enhanced Alignment
- Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders
- Interpretability and Generalization Bounds for Learning Spatial Physics
- A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning
- Mechanistic Interpretability in the Presence of Architectural Obfuscation
- Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)
- Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference
- Validating Mechanistic Interpretations: An Axiomatic Approach
- Six Fallacies in Substituting Large Language Models for Human Participants
- Mechanistic Interpretability of Diffusion Models: Circuit-Level Analysis and Causal Validation
- From memories to maps: Mechanisms of in context reinforcement learning in transformers
- Measuring and Guiding Monosemanticity
- Emergent collective dynamics from motile photokinetic organisms
- Mechanistic Interpretability Needs Philosophy
- Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition
- Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
- Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
- Bilinear MLPs enable weight-based mechanistic interpretability
- From Memories to Maps: Mechanisms of In-Context Reinforcement Learning in Transformers
- Amortizing personalization in virtual brain twins
- Stochastic Parameter Decomposition
- Understanding Verbatim Memorization in LLMs Through Circuit Discovery
- Mechanistic Interpretability of Emotion Inference in Large Language Models
- Data-Driven Multiscale Topology Optimization of Spinodoid Architected Materials with Controllable Anisotropy
- SAFER: Probing Safety in Reward Models with Sparse Autoencoder
- Prompting as Scientific Inquiry
- Emerging AI Approaches for Cancer Spatial Omics
- Learning Modular Exponentiation with Transformers
- Constraint-Guided Symbolic Regression for Data-Efficient Kinetic Model Discovery
- Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability
- Circuit-tuning: A Mechanistic Approach for Identifying Parameter Redundancy and Fine-tuning Neural Networks
- Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs
- Scientific Machine Learning of Chaotic Systems Discovers Governing Equations for Neural Populations
- Quantifying Cross-Attention Interaction in Transformers for Interpreting TCR-pMHC Binding
- Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs
- Dynamical Archetype Analysis: Autonomous Computation
- A statistical approach to latent dynamic modeling with differential equations
- The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?
- Mechanistic Indicators of Understanding in Large Language Models
- Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers
- Towards Interpretable Drug-Drug Interaction Prediction: A Graph-Based Approach with Molecular and Network-Level Explanations
- Simulation as Supervision: Mechanistic Pretraining for Scientific Discovery
- A PBN-RL-XAI Framework for Discovering a "Hit-and-Run" Therapeutic Strategy in Melanoma
- Propensity score weighting across counterfactual worlds: longitudinal effects under positivity violations
- Mechanistic Interpretability of LoRA-Adapted Language Models for Nuclear Reactor Safety Applications
- Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning
- CytoSAE: Interpretable Cell Embeddings for Hematology
- FADE: Why Bad Descriptions Happen to Good Features
- Tracing Facts or just Copies? A critical investigation of the Competitions of Mechanisms in Large Language Models
- Teach Old SAEs New Domain Tricks with Boosting
- Insights into a radiology-specialised multimodal large language model with sparse autoencoders
- Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility
- Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
- Understanding Matching Mechanisms in Cross-Encoders
- Decoding Translation-Related Functional Sequences in 5'UTRs Using Interpretable Deep Learning Models
- Probing Ranking LLMs: A Mechanistic Analysis for Information Retrieval
- Deep Learning for Blood-Brain Barrier Permeability Prediction
- Residual Koopman Model Predictive Control for Enhanced Vehicle Dynamics with Small On-Track Data Input
- CircuitProbe: Dissecting Spatiotemporal Visual Semantics with Circuit Tracing
- HumorDB: Can AI understand graphical humor?
- Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
- A nonparametric approach to practical identifiability of nonlinear mixed effects models
- Large Language Models Are Human-Like Internally
- How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation
- Can You Trust an LLM with Your Life-Changing Decision? An Investigation into AI High-Stakes Responses
- Semiclassical Spin Exchange via Temperature-Dependent Transition States
- Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders
- Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes
- How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
- Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning
- Modeling the Temperature-Humidity Coupling Dynamics of Soybean Pod Borer Population and Assessing the Predictive Performance of the PCM-NN Algorithm
- I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
- Covariance spectrum in nonlinear recurrent neural networks
- Discovery of Disease Relationships via Transcriptomic Signature Analysis Powered by Agentic AI
- Evaluating and Designing Sparse Autoencoders by Approximating Quasi-Orthogonality
- Surgical Knowledge Rewrite in Compact LLMs: An 'Unlearn-then-Learn' Strategy with (IA^3IA^3) for Localized Factual Modulation and Catastrophic Forgetting Mitigation
- Activation Steering for Bias Mitigation: An Interpretable Approach to Safer LLMs
- Entangled in Representations: Mechanistic Investigation of Cultural Biases in Large Language Models
- BiasGym: Fantastic Biases and How to Find (and Remove) Them
- From Transformer to Biology: A Hierarchical Model for Attention in Complex Problem-Solving
- How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
- Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders
- BiasGym: Fantastic LLM Biases and How to Find (and Remove) Them
- eDIF: A European Deep Inference Fabric for Remote Interpretability of LLM
- Maximum Entropy Models for Unimodal Time Series: Case Studies of Universe 25 and St. Matthew Island
- Mantis: A Simulation-Grounded Foundation Model for Disease Forecasting
- CALYPSO: Forecasting and Analyzing MRSA Infection Patterns with Community and Healthcare Transmission Dynamics
- Counterfactual Probabilistic Diffusion with Expert Models
- Modeling GRNs with a Probabilistic Categorical Framework
- Disentangling concept semantics via multilingual averaging in Sparse Autoencoders
- LLMSymGuard: A Symbolic Safety Guardrail Framework Leveraging Interpretable Jailbreak Concepts
- From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits
- Fidelity Isn't Accuracy: When Linearly Decodable Functions Fail to Match the Ground Truth
- Beyond Transcription: Mechanistic Interpretability in ASR
- Mechanistic Exploration of Backdoored Large Language Model Attention Patterns
- KL-based self-distillation for large language models
- Adversarial Examples Are Not Bugs, They Are Superposition
- LLM Assertiveness can be Mechanistically Decomposed into Emotional and Logical Components
- Disentangling Polysemantic Neurons with a Null-Calibrated Polysemanticity Index and Causal Patch Interventions
- Rethinking scale in network neuroscience: Contributions and opportunities at the nanoscale
- Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability
- Biologically Disentangled Multi-Omic Modeling Reveals Mechanistic Insights into Pan-Cancer Immunotherapy Resistance
- Tracing Positional Bias in Financial Decision-Making: Mechanistic Insights from Qwen2.5
- Linear Power System Modeling and Analysis Across Wide Operating Ranges: A Hierarchical Neural State-Space Equation Approach
- Even Heads Fix Odd Errors: Mechanistic Discovery and Surgical Repair in Transformer Attention
- RelP: Faithful and Efficient Circuit Discovery via Relevance Patching
- Prompt the Unseen: Evaluating Visual-Language Alignment Beyond Supervision
- Mechanistic interpretability for steering vision-language-action models
- Can LLMs Lie? Investigation beyond Hallucination
- Challenges in Understanding Modality Conflict in Vision-Language Models
- Non-Linear Model-Based Sequential Decision-Making in Agriculture
- Preserving Bilinear Weight Spectra with a Signed and Shrunk Quadratic Activation Function
- Pulling Back the Curtain on ReLU Networks
- Sparse Autoencoder Neural Operators: Model Recovery in Function Spaces
- Personality as a Probe for LLM Evaluation: Method Trade-offs and Downstream Effects
- Interpreting Transformer Architectures as Implicit Multinomial Regression
- ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders
- Towards explainable decision support using hybrid neural models for logistic terminal automation
- Measuring Uncertainty in Transformer Circuits with Effective Information Consistency
- Think-to-Talk or Talk-to-Think? When LLMs Come Up with an Answer in Multi-Hop Arithmetic Reasoning
- Data-driven discovery of dynamical models in biology
- Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors
- The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis
- Interpretability as Alignment: Making Internal Understanding a Design Principle
- Behind the Scenes: Mechanistic Interpretability of LoRA-adapted Whisper for Speech Emotion Recognition
- Decoding the Stability of Transition-Metal Alloys with Theory-infused Deep Learning
- An Agentic AI Workflow to Simplify Parameter Estimation of Complex Differential Equation Systems
- Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal
- The power of dynamic causality in observer-based design for soft sensor applications
- Modelling Under-Reported Data: Pitfalls of Naïve Approaches and a New Statistical Framework for Epidemic Curve Reconstruction
- The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features
- Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content
- Swarm Intelligence for Chemical Reaction Optimisation
- Unified Spatiotemopral Physics-Informed Learning (USPIL): A Framework for Modeling Complex Predator-Prey Dynamics
- Learning Mechanistic Subtypes of Neurodegeneration with a Physics-Informed Variational Autoencoder Mixture Model
- Unified Spatiotemporal Physics-Informed Learning (USPIL): A Framework for Modeling Complex Predator-Prey Dynamics
- Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models
- DeepMech: A Machine Learning Framework for Chemical Reaction Mechanism Prediction
- Modeling Transformers as complex networks to analyze learning dynamics
- Bayesian Calibration and Model Assessment of Cell Migration Dynamics with Surrogate Model Integration
- Learning From Simulators: A Theory of Simulation-Grounded Learning
- Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing
- Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models
- Tikhonov-Fenichel Reductions and their Application to a Novel Modelling Approach for Mutualism
- A Machine Learning Framework for Pathway-Driven Therapeutic Target Discovery in Metabolic Disorders
- From Parameters to Performance: A Data-Driven Study on LLM Structure and Development
- Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework
- BioBO: Biology-informed Bayesian Optimization for Perturbation Design
- Interpreting ResNet-based CLIP via Neuron-Attention Decomposition
- Integrating Mechanistic Modeling and Machine Learning to Study CD4+/CD8+ CAR-T Cell Dynamics with Tumor Antigen Regulation
- Fine-Tuning is Subgraph Search: A New Lens on Learning Dynamics
- Binary Autoencoder for Mechanistic Interpretability of Large Language Models
- CLUE: Conflict-guided Localization for LLM Unlearning Framework
- Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates
- GALAX: Graph-Augmented Language Model for Explainable Reinforcement-Guided Subgraph Reasoning in Precision Medicine
- Towards Atoms of Large Language Models
- RAPTOR-GEN: RApid PosTeriOR GENerator for Bayesian Learning in Biomanufacturing
- Concept-SAE: Active Causal Probing of Visual Model Behavior
- Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation
- Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
- Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare
- Hedonic Neurons: A Mechanistic Mapping of Latent Coalitions in Transformer MLPs
- LLM Interpretability with Identifiable Temporal-Instantaneous Representation
- Mechanistic Fine-tuning for In-context Learning
- Bayesian Inference for Sexual Contact Networks Using Longitudinal Survey Data
- Toward a Theory of Generalizability in LLM Mechanistic Interpretability Research
- Thrust based on changes in angular momentum
- Latent Concept Disentanglement in Transformer-based Language Models
- ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
- Minimalist Explanation Generation and Circuit Discovery
- Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions
- Circuit-Aware Reward Training: A Mechanistic Framework for Longtail Robustness in RLHF
- Excitonic Energy Transfer in Red Algal Photosystem I Reveals an Evolutionary Bridge between Cyanobacteria and Plants
- Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis
- From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning
- Measuring Sparse Autoencoder Feature Sensitivity
- Cyclic Ablation: Testing Concept Localization against Functional Regeneration in AI
- Mechanistic Interpretability as Statistical Estimation: A Variance Analysis of EAP-IG
- Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models
- Feature Identification via the Empirical NTK
- Commutative algebra neural network reveals genetic origins of diseases
- Interpret, prune and distill Donut : towards lightweight VLMs for VQA on document
- BioBlobs: Differentiable Graph Partitioning for Protein Representation Learning
- When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models
- Integrative modelling of biomolecular dynamics
- Interpreting Language Models Through Concept Descriptions: A Survey
- Neural Theorem Proving: Generating and Structuring Proofs for Formal Verification
- Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks
- Understanding Addition and Subtraction in Transformers
- Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders
- Learning Explicit Single-Cell Dynamics Using ODE Representations
- Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models
- Towards CONUS-Wide ML-Augmented Conceptually-Interpretable Modeling of Catchment-Scale Precipitation-Storage-Runoff Dynamics
- Deep learning for flash drought forecasting and interpretation
- Mechanistic Interpretability of Socio-Political Frames in Language Models
- Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test
- The Argument is the Explanation: Structured Argumentation for Trust in Agents
- Disentangling Recall and Reasoning in Transformer Models through Layer-wise Attention and Activation Analysis
- Decomposing Attention To Find Context-Sensitive Neurons
- SoC-DT: Standard-of-Care Aligned Digital Twins for Patient-Specific Tumor Dynamics
- Discovering Transformer Circuits via a Hybrid Attribution and Pruning Framework
- Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models
- Mechanistic-statistical inference of mosquito dynamics from mark-release-recapture data
- Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
- The Logical Implication Steering Method for Conditional Interventions on Transformer Generation
- Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning
- Causal Abstractions, Categorically Unified
- Visual Representations inside the Language Model
- BlackboxNLP-2025 MIB Shared Task: Exploring Ensemble Strategies for Circuit Localization Methods
- Tug-of-war between idioms' figurative and literal interpretations in LLMs
- ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall
- Advancing AI Research Assistants with Expert-Involved Learning
- Biology-driven assessment of deep learning super-resolution imaging of the porosity network in dentin
- Iterated Agent for Symbolic Regression
- RADAR: Mechanistic Pathways for Detecting Data Contamination in LLM Evaluation
- InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
- Egocentric Visual Navigation through Hippocampal Sequences
- Causality \neq\neq Decodability, and Vice Versa: Lessons from Interpreting Counting ViTs
- Impact of Oxygen on DNA Damage Distribution in 3D Genome and Its Correlation to Oxygen Enhancement Ratio under High LET Irradiation
- Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability
- QLENS: Towards A Quantum Perspective of Language Transformers
- A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models
- Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
- Data-Driven Topology Optimization for Multiscale Biomimetic Spinodal Design
- Physical models of embryonic epithelial healing: A review
- Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
- Multi-Scale Probabilistic Generation Theory: A Unified Information-Theoretic Framework for Hierarchical Structure in Large Language Models
- Constrained belief updates explain geometric structures in transformer representations
- CAST: Compositional Analysis via Spectral Tracking for Understanding Transformer Layer Functions
- Functional and parametric identifiability for universal differential equations applied to chemical reaction networks
- Unlocking Out-of-Distribution Generalization in Transformers via Recursive Latent Space Reasoning
- Circuit Insights: Towards Interpretability Beyond Activations
- Causal Time Series Modeling of Supraglacial Lake Evolution in Greenland under Distribution Shift
- Game-Theoretic Discovery of Quantum Error-Correcting Codes Through Nash Equilibria
- Intrinsic Self-Correction in LLMs: Towards Explainable Prompting via Mechanistic Interpretability
- DePass: Unified Feature Attributing by Simple Decomposed Forward Pass
- Extracting Rule-based Descriptions of Attention Features in Transformers
- How role-play shapes relevance judgment in zero-shot LLM rankers
- Layer Specialization Underlying Compositional Reasoning in Transformers
- Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations
- Fighter: Unveiling the Graph Convolutional Nature of Transformers in Time Series Modeling
- Atomic Literary Styling: Mechanistic Manipulation of Prose Generation in Neural Language Models
- Base Models Know How to Reason, Thinking Models Learn When
- I Spy With My Model's Eye: Visual Search as a Behavioural Test for MLLMs
- A Class of Markovian Self-Reinforcing Processes with Power-Law Distributions
- Prospects for Using Artificial Intelligence to Understand Intrinsic Kinetics of Heterogeneous Catalytic Reactions
- Foundation Models for Discovery and Exploration in Chemical Space
- Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
- MolBridge: Atom-Level Joint Graph Refinement for Robust Drug-Drug Interaction Event Prediction
- Stream: Scaling up Mechanistic Interpretability to Long Context in LLMs via Sparse Attention
- Some Attention is All You Need for Retrieval
- Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers
- ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
- Mapping Faithful Reasoning in Language Models
- Transformer brain encoders explain human high-level visual responses
- Mechanistic Interpretability for Neural TSP Solvers
- Mechanism-Guided Residual Lifting and Control Consistent Modeling for Pneumatic Drying Processes
- Overshoot-resolved transition modeling based on field inversion and symbolic regression
- Learning Interpretable Features in Audio Latent Spaces via Sparse Autoencoders
- PAHQ: Accelerating Automated Circuit Discovery through Mixed-Precision Inference Optimization
- Interpreting and Mitigating Unwanted Uncertainty in LLMs
- Sparsity and Superposition in Mixture of Experts
- Mechanistic Interpretability of RNNs emulating Hidden Markov Models
- FaCT: Faithful Concept Traces for Explaining Neural Network Decisions
- Emergence of Minimal Circuits for Indirect Object Identification in Attention-Only Transformers
- Large Language Models Report Subjective Experience Under Self-Referential Processing
- RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching
- Chain-of-Thought Hijacking
- In Defence of Post-hoc Explainability
- MedSAE: Dissecting MedCLIP Representations with Sparse Autoencoders
- BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection
- StreetMath: Study of LLMs' Approximation Behaviors
- Modelling ion channels with a view towards identifiability
- Atlas-Alignment: Making Interpretability Transferable Across Language Models
- Pregnancy as a dynamical paradox: robustness, control and birth onset
- Space as Time Through Neuron Position Learning
- TRISKELION-1: Unified Descriptive-Predictive-Generative AI
- Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI
- Automatically Finding Rule-Based Neurons in OthelloGPT
- Causal Graph Neural Networks for Healthcare
- Interpreting Emergent Features in Deep Learning-based Side-channel Analysis
- LLM Probing with Contrastive Eigenproblems: Improving Understanding and Applicability of CCS
- Addressing divergent representations from causal interventions on neural networks
- APP: Accelerated Path Patching with Task-Specific Pruning
- SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models
- Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning
- Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation
- The Trilemma of Truth in Large Language Models
- SCALAR: Benchmarking SAE Interaction Sparsity in Toy LLMs
- Automated Circuit Interpretation via Probe Prompting
- Rank-1 LoRAs Encode Interpretable Reasoning Signals
- Learning Biomolecular Motion: The Physics-Informed Machine Learning Paradigm
- Visual Exploration of Feature Relationships in Sparse Autoencoders with Curated Concepts
- Fractional neural attention for efficient multiscale sequence processing
- Group Equivariance Meets Mechanistic Interpretability: Equivariant Sparse Autoencoders
- Decomposition of Small Transformer Models
- Weight-sparse transformers have interpretable circuits
- An Automated Framework for Analyzing Structural Evolution in On-the-fly Non-adiabatic Molecular Dynamics Using Autoencoder and Multiple Molecular Descriptors
- Bridging the genotype-phenotype gap with generative artificial intelligence
- From Black-Box to White-Box: Control-Theoretic Neural Network Interpretability
- Explainable deep learning framework for cancer therapeutic target prioritization leveraging PPI centrality and node embeddings
- Comment on "Repair of DNA Double-Strand Breaks Leaves Heritable Impairment to Genome Function"
- Which Sparse Autoencoder Features Are Real? Model-X Knockoffs for False Discovery Rate Control
- Differentiable Electrochemistry: A paradigm for uncovering hidden physical phenomena in electrochemical systems
- nnterp: A Standardized Interface for Mechanistic Interpretability of Transformers
- Judicial Sentencing Prediction Based on Hybrid Models and Two-Stage Learning Algorithms
- Chromatographic Peak Shape from Stochastic Model: Analytic Time-Domain Expression in Terms of Physical Parameters and Conditions under which Heterogeneity Reduces Tailing
- Beyond Protein Language Models: An Agentic LLM Framework for Mechanistic Enzyme Design
- Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks
- Interpreting GFlowNets for Drug Discovery: Extracting Actionable Insights for Medicinal Chemistry
- Pathway to Relevance: How Cross-Encoders Implement a Semantic Variant of BM25
- Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models
- Vector Arithmetic in Concept and Token Subspaces
- The Horcrux: Mechanistically Interpretable Task Decomposition for Detecting and Mitigating Reward Hacking in Embodied AI Systems
- Understanding Counting Mechanisms in Large Language and Vision-Language Models
- BlockCert: Certified Blockwise Extraction of Transformer Mechanisms
- Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits
- Approximate Bayesian Computation Made Easy: A Practical Guide to ABC-SMC for Dynamical Systems with \texttt{pymc}
- Mechanistic Interpretability for Transformer-based Time Series Classification
- Physics Steering: Causal Control of Cross-Domain Concepts in a Physics Foundation Model
- Interpretability for Time Series Transformers using A Concept Bottleneck Framework
- Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations
- A race to belief: How Evidence Accumulation shapes trust in AI and Human informants
- FoldSAE: Learning to Steer Protein Folding Through Sparse Representations
- Unsupervised decoding of encoded reasoning using language model interpretability
- TrendGNN: Towards Understanding of Epidemics, Beliefs, and Behaviors
- VCWorld: A Biological World Model for Virtual Cell Simulation
- EXP-CAM: Explanation Generation and Circuit Discovery Using Classifier Activation Matching
- HyperADRs: A Hierarchical Hypergraph Framework for Drug-Gene-ADR Prediction
- ProteinPNet: Prototypical Part Networks for Concept Learning in Spatial Proteomics
- Translating Measures onto Mechanisms: The Cognitive Relevance of Higher-Order Information
- Mechanisms of Symbol Processing for In-Context Learning in Transformer Networks
- Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability
- Approximate Bayesian Inference on Mechanisms of Network Growth and Evolution
- AtomDisc: An Atom-level Tokenizer that Boosts Molecular LLMs and Reveals Structure--Property Associations
- Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN
- Neural Policy Composition from Free Energy Minimization
- Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective
- Minuet: A Diffusion Autoencoder for Compact Semantic Compression of Multi-Band Galaxy Images
- Sparse Attention Post-Training for Mechanistic Interpretability
- Mechanistic Interpretability of Antibody Language Models Using SAEs
- Rethinking Sparse Autoencoders: Select-and-Project for Fairness and Control from Encoder Features Alone
- On the Theoretical Foundation of Sparse Dictionary Learning in Mechanistic Interpretability
- A network-driven framework for enhancing gene-disease association studies in coronary artery disease
- XMCQDPT2-Fidelity Transfer-Learning Potentials and a Wavepacket Oscillation Model with Power-Law Decay for Ultrafast Photodynamics
- ExPUFFIN: Thermodynamic Consistent Viscosity Prediction in an Extended Path-Unifying Feed-Forward Interfaced Network
- Mechanistic Interpretability of GPT-2: Lexical and Contextual Layers in Sentiment Analysis
- Same Content, Different Answers: Cross-Modal Inconsistency in MLLMs
- A microstructural rheological model for transient creep in polycrystalline ice
- Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
- Bayesian Co-Navigation of a Computational Physical Model and AFM Experiment to Autonomously Survey a Combinatorial Materials Library
- Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignment
- SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation
- Interpretable and Steerable Concept Bottleneck Sparse Autoencoders
- Unlocking the Address Book: Dissecting the Sparse Semantic Structure of LLM Key-Value Caches via Sparse Autoencoders
- SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation
- Physics-informed neural network for fatigue life prediction of irradiated austenitic and ferritic/martensitic steels
- ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts
- Learning continuous SOC-dependent thermal decomposition kinetics for Li-ion cathodes using KA-CRNNs
- Who is In Charge? Dissecting Role Conflicts in Instruction Following
- SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks
- AI Epidemiology: achieving explainable AI through expert oversight patterns
- Machine Learning Framework for Thrombosis Risk Prediction in Rotary Blood Pumps
- RP-CATE: Recurrent Perceptron-based Channel Attention Transformer Encoder for Industrial Hybrid Modeling
- R-GenIMA: Integrating Neuroimaging and Genetics with Interpretable Multimodal AI for Alzheimer's Disease Progression
- Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability
- Block-Recurrent Dynamics in Vision Transformers
- Sign-Aware Multistate Jaccard Kernels and Geometry for Real and Complex-Valued Signals
- The Deepfake Detective: Interpreting Neural Forensics Through Sparse Features and Manifolds
- Omni-Weather: Unified Multimodal Foundation Model for Weather Generation and Understanding
- Information is localized in growing network models
- Mono- and Polyauxic Growth Kinetics: A Semi-Mechanistic Framework for Complex Biological Dynamics
- Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation
- Mechanistic Analysis of Circuit Preservation in Federated Learning
- A Paradigm Shift in Human Neuroscience Research: Progress, Prospects, and a Proof of Concept for Population Neuroscience
- EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs
- Triangulation as an Acceptance Rule for Multilingual Mechanistic Interpretability
- BIOME-Bench: A Benchmark for Biomolecular Interaction Inference and Multi-Omics Pathway Mechanism Elucidation from Scientific Literature
- Connecting strain rate dependence of fcc metals to dislocation avalanche signatures
- Towards mechanistic understanding in a data-driven weather model: internal activations reveal interpretable physical features
- "X-ray Coulomb Counting" to understand electrochemical systems
- Bridging Visual Intuition and Chemical Expertise: An Autonomous Analysis Framework for Nonadiabatic Dynamics Simulations via Mentor-Engineer-Student Collaboration
- Adversarial Lens: Exploiting Attention Layers to Generate Adversarial Examples for Evaluation
- Emergent World Beliefs: Exploring Transformers in Stochastic Games
- How much neuroscience does a neuroscientist need to know?
- Trustworthy Data-Driven Wildfire Risk Prediction and Understanding in Western Canada
- Central Dogma Transformer: Towards Mechanism-Oriented AI for Cellular Understanding
- Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models
- When the Coffee Feature Activates on Coffins: An Analysis of Feature Extraction and Steering for Mechanistic Interpretability
- Mechanistic Interpretability of Large-Scale Counting in LLMs through a System-2 Strategy
- Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencoders
- Bridging Mechanistic Interpretability and Prompt Engineering with Gradient Ascent for Interpretable Persona Control
- A Pre-trained Reaction Embedding Descriptor Capturing Bond Transformation Patterns
- Local Multimodal Dynamics in Mixed Ionic-Electronic Conductors and Their Fingerprints in Organic Electrochemical Transistor Operation
- When Models Manipulate Manifolds: The Geometry of a Counting Task
- Interpreting Transformers Through Attention Head Intervention
- Analytical review of nanoplastic bioaccumulation data and a unified toxicokinetic model: from teleosts to human brain
- Molecular signatures of pressure-induced phase transitions in a lipid bilayer
- A Backpropagation-Free Feedback-Hebbian Network for Continual Learning Dynamics
- AlignSAE: Concept-Aligned Sparse Autoencoders
- Physics-constrained Gaussian Processes for Predicting Shockwave Hugoniot Curves
- Time Travel Engine: A Shared Latent Chronological Manifold Enables Historical Navigation in Large Language Models
- Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers
- LLM-Powered Social Digital Twins: A Framework for Simulating Population Behavioral Response to Policy Interventions
- Vocabulary Expansion of Large Language Models via Kullback-Leibler-Based Self-Distillation
- Toward Understanding Unlearning Difficulty: A Mechanistic Perspective and Circuit-Guided Difficulty Metric
- Where Knowledge Collides: A Mechanistic Study of Intra-Memory Knowledge Conflict in Language Models
- Diagnosing Generalization Failures in Fine-Tuned LLMs: A Cross-Architectural Study on Phishing Detection
- Dedifferentiation stabilizes stem cell lineages: From CTMC to diffusion theory and thresholds
- An Epidemiological Modeling Take on Religion Dynamics
- From Adversarial Poetry to Adversarial Tales: An Interpretability Research Agenda
- Metabolomic Biomarker Discovery for ADHD Diagnosis Using Interpretable Machine Learning
- Mechanistic Learning for Survival Prediction in NSCLC Using Routine Blood Biomarkers and Tumor Kinetics
- From Interpretability to Performance: Optimizing Retrieval Heads for Long-Context Language Models
- Reasoning Models Generate Societies of Thought
- BACH-V: Bridging Abstract and Concrete Human-Values in Large Language Models
- Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
- Patterning: The Dual of Interpretability
- Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition
- The Physics of the Dancing \emph{Deity}: Coupled Oscillators in Himalayan Processions
- Race, Ethnicity and Their Implication on Bias in Large Language Models
- A Machine Learning--Based Surrogate EKMA Framework for Diagnosing Urban Ozone Formation Regimes: Evidence from Los Angeles
- Long-term prediction of ENSO with physics-guided Deep Echo State Networks
- Persistent Sheaf Laplacian Analysis of Protein Stability and Solubility Changes upon Mutation
- Single-Node Wilson--Cowan Model Accounts for Speech-Evoked γγ-Band Deficits in Schizophrenia
- LLM Powered Social Digital Twins: A Framework for Simulating Population Behavioral Response to Policy Interventions
- DiSPA: Differential Substructure-Pathway Attention for Drug Response Prediction
- White-Box mHC: Electromagnetic Spectrum-Aware and Interpretable Stream Interactions for Hyperspectral Image Classification
- Emergence and Evolution of Interpretable Concepts in Diffusion Models
- Latent Causal Diffusions for Single-Cell Perturbation Modeling
- A Monosemantic Attribution Framework for Stable Interpretability in Clinical Neuroscience Large Language Models
- Interpretability of the Intent Detection Problem: A New Approach
- Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers
- How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability
- Data-driven sparse identification of vector-borne disease dynamics with memory effects
- Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs
- Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures
- Putting a Face to Forgetting: Continual Learning meets Mechanistic Interpretability
- Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
- Amortized Spectral Kernel Discovery via Prior-Data Fitted Network
- A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima
- A Multi-agent Framework for Physical Laws Discovery
- Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models
- Sparse or Dense? A Mechanistic Estimation of Computation Density in Transformer-based LLMs
- Beyond Conditional Computation: Retrieval-Augmented Genomic Foundation Models with Gengram
- BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Elicitation
- Universal Redundancies in Time Series Foundation Models
- Mechanistic Interpretability of Brain-to-Speech Models Across Speech Modes
- Toward Interpretable and Generalizable AI in Regulatory Genomics
- Supervised sparse auto-encoders as unconstrained feature models for semantic composition
- Agentic Framework for Epidemiological Modeling
- Explaining the Explainer: Understanding the Inner Workings of Transformer-based Symbolic Regression Models
- Mechanistic Interpretability as Statistical Estimation: A Variance Analysis
- MARADONER: Motif Activity Response Analysis Done Right
- BioGen: An Evidence-Grounded Framework for Interpreting RNA-seq Gene Clusters in Antimicrobial Resistance Research
- Disentangling meaning from language in LLM-based machine translation
- Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish
- PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling
- DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
- From Vision to Decision: Neuromorphic Control for Autonomous Navigation and Tracking
- Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities
- A waveguide kinetics framework for electrochemical polarization
- Somatic Mechanotherapy Activates a Spatiotemporally Synchronized CPTC Wnt Axis for Gut Regeneration
- Causal Front-Door Adjustment for Robust Jailbreak Attacks on LLMs
- Advancing Opinion Dynamics Modeling with Neural Diffusion-Convection-Reaction Equation
- Path Sampling for Rare Events Boosted by Machine Learning
- Explanations are a Means to an End: Decision Theoretic Explanation Evaluation
- Momentum Attention: The Physics of In-Context Learning and Spectral Forensics for Mechanistic Interpretability
- The Quantum Sieve Tracer: A Hybrid Framework for Layer-Wise Activation Tracing in Large Language Models
- Habitat heterogeneity and dispersal network structure as drivers of metacommunity dynamics
- How (Not) to Hybridize Neural and Mechanistic Models for Epidemiological Forecasting
- Reasoning aligns language models to human cognition
- How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location
- Patches of Nonlinearity: Instruction Vectors in Large Language Models
- Revisiting Transformers with Insights from Image Filtering and Boosting
- Towards Understanding Multimodal Fine-Tuning: Spatial Features
- CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs
- Learning Alzheimer's Disease Signatures by bridging EEG with Spiking Neural Networks and Biophysical Simulations
- CPTCs Drive Somatic-Visceral Communication via the Wnt Axis in Somatic Mechanotherapy: A Single-Cell Deep Learning Study
- Tiny Moves: Game-based Hypothesis Refinement
- From Circuits to Dynamics: Understanding and Stabilizing Failure in 3D Diffusion Transformers
- Can Large Language Models Make Everyone Happy?
- Med-SegLens: Latent-Level Model Diffing for Interpretable Medical Image Segmentation
- Control Reinforcement Learning: Token-Level Mechanistic Analysis via Learned SAE Feature Steering
- EVA: Towards a universal model of the immune system
- DEpiABS: Differentiable Epidemic Agent-Based Simulator
- Protein Circuit Tracing via Cross-layer Transcoders
- Dopamine: Brain Modes, Not Brains
- Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features
- Revealing Exotic Nanophase Iron in Lunar Samples Through Impact-Driven Spatial Fingerprints
- Learning Glioblastoma Tumor Heterogeneity Using Brain Inspired Topological Neural Networks
- Layer-Specific Fine-Tuning for Improved Negation Handling in Medical Vision-Language Models
- Inner Loop Inference for Pretrained Transformers: Unlocking Latent Capabilities Without Training
- Predicting Company Growth using Scaling Theory informed Machine Learning
- Singular Vectors of Attention Heads Align with Features
- Finding Highly Interpretable Prompt-Specific Circuits in Language Models
- What Do Neurons Listen To? A Neuron-level Dissection of a General-purpose Audio Model
- Seeing to Generalize: How Visual Data Corrects Binding Shortcuts
- Universal Framework for Decomposing Ionic Transport into Interpretable Mechanisms
- Systematic Evaluation of Single-Cell Foundation Model Interpretability Reveals Attention Captures Co-Expression Rather Than Unique Regulatory Signal
- Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy
- Exploring Memory Effects: Sparse Identification in Vector-Borne Diseases
- Discovering Universal Activation Directions for PII Leakage in Language Models
- On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking
- Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees
- Quantifying LLM Attention-Head Stability: Implications for Circuit Universality
- A Probabilistic Framework for LLM-Based Model Discovery
- Simplifying Outcomes of Language Model Component Analyses with ELIA
- Mechanistic Interpretability with Sparse Autoencoder Neural Operators
- Hiding in Plain Text: Detecting Concealed Jailbreaks via Activation Disentanglement
- Beyond Behavioural Trade-Offs: Mechanistic Tracing of Pain-Pleasure Decisions in an LLM
- Temperature as a Dynamically Maintained Steady State: Photonic Mechanisms, Maintenance Cost, and the Limits of the Infinite-Reservoir Idealization
- Unveiling Scaling Laws of Parameter Identifiability and Uncertainty Quantification in Data-Driven Biological Modeling
- Robust Model Selection for Discovery of Latent Mechanistic Processes
- ABM-UDE: Developing Surrogates for Epidemic Agent-Based Models via Scientific Machine Learning
- MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning
- SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented Evaluation
- MetaOthello: A Controlled Study of Multiple World Models in Transformers
- Certified Circuits: Stability Guarantees for Mechanistic Circuits
- Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks
- Transformers converge to invariant algorithmic cores
- AR&D: A Framework for Retrieving and Describing Concepts for Interpreting AudioLLMs
- On De-Individuated Neurons: Continuous Symmetries Enable Dynamic Topologies
- Diagnosing Generalization Failures from Representational Geometry Markers
- Emerging Human-like Strategies for Semantic Memory Foraging in Large Language Models
- Decoding Answers Before Chain-of-Thought: Evidence from Pre-CoT Probes and Activation Steering
- Interpretable Cross-Network Attention for Resting-State fMRI Representation Learning
- Emergence of Spatial Representation in an Actor-Critic Agent with Hippocampus-Inspired Sequence Generator
- A Closed-loop Framework to Discriminate Models Using Optimal Control
- What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models
- Inferring brain plasticity rule under long-term stimulation with structured recurrent dynamics
- TumorFlow: Physics-Guided Longitudinal MRI Synthesis of Glioblastoma Growth
- Tracing Pharmacological Knowledge In Large Language Models
- Observing and Controlling Features in Vision-Language-Action Models
- The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology
- BioLLMAgent: A Hybrid Framework with Enhanced Structural Interpretability for Simulating Human Decision-Making in Computational Psychiatry
- Stochastic Optimal Feedforward-Feedback Control for Partially Observable Sensorimotor Systems
- Steering Awareness: Models Can Be Trained to Detect Activation Steering
- Lost in Translation: Simulation-Informed Bayesian Inference Improves Understanding of Molecular Motion From Neutron Scattering
- The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR\rightarrow\rightarrowLLM Pipelines?
- Learning Concept Bottleneck Models from Mechanistic Explanations
- Are Audio-Language Models Listening? Audio-Specialist Heads for Adaptive Audio Steering
- Causal Interpretation of Neural Network Computations with Contribution Decomposition
- Computational Multi-Agents Society Experiments: Social Modeling Framework Based on Generative Agents
- Physical Models of Embryonic Epithelial Healing
- Fast reconstruction of degenerate populations of conductance-based neuron models from spike times
- The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs
- Distilled Circuits: A Mechanistic Study of Internal Restructuring in Knowledge Distillation
- Protein Counterfactuals via Diffusion-Guided Latent Optimization
- Backdoor Directions in Vision Transformers
- Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness
- Implicit Statistical Inference in Transformers: Approximating Likelihood-Ratio Tests In-Context
- Discovery of a Hematopoietic Manifold in scGPT Yields a Method for Extracting Performant Algorithms from Biological Foundation Model Internals
- From Data Statistics to Feature Geometry: How Correlations Shape Superposition
- The Affine Divergence: Aligning Activation Updates Beyond Normalisation
- Dissecting Chronos: Sparse Autoencoders Reveal Causal Feature Hierarchies in Time Series Foundation Models
- Exhaustive Circuit Mapping of a Single-Cell Foundation Model Reveals Massive Redundancy, Heavy-Tailed Hub Architecture, and Layer-Dependent Differentiation Control
- Chem4DLLM: 4D Multimodal LLMs for Chemical Dynamics Understanding
- ELISA: An Interpretable Hybrid Generative AI Agent for Expression-Grounded Discovery in Single-Cell Genomics
- Locating Demographic Bias at the Attention-Head Level in CLIP's Vision Encoder
- Size-Dependent Fluorescence Kinetics Reveal Contributions of Intrinsic Quenching and Singlet-Triplet Annihilation during LHCII Aggregation
- Attention Gathers, MLPs Compose: A Causal Analysis of an Action-Outcome Circuit in VideoViT
- Hydrogen-atom roaming reactions in water clusters: Unveiling an unusual dimension of water reactivity through first-principles calculations and machine learning
- Deep Learning for Blood-Brain Barrier Permeability Prediction: From Discriminative Models to Mechanism-Aware Design
- Mechanistic Foundations of Goal-Directed Control
- Directional Routing in Transformers
- A minimal model of pump foil dynamics
- LLM-Powered Flood Depth Estimation from Social Media Imagery: A Vision-Language Model Framework with Mechanistic Interpretability for Transportation Resilience
- Intracellular Measurement-Informed Multiscale Modeling for Scalable iPSC Manufacturing
- Improving Epidemic Analyses with Privacy-Preserving Integration of Sensitive Data
- Bridging Crystal Structure and Material Properties via Bond-Centric Descriptors
- Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
- From Snapshots to Symphonies: The Evolution of Protein Prediction from Static Structures to Generative Dynamics and Multimodal Interactions
- Interpretability without actionability: mechanistic methods cannot correct language model errors despite near-perfect internal representations
- Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients
- Do Language Models Encode Semantic Relations? Probing and Sparse Feature Analysis
- Fundamental Limits of Neural Network Sparsification: Evidence from Catastrophic Interpretability Collapse
- Causal Intervention Framework for Variational Auto Encoder Mechanistic Interpretability
- Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models
- Interpreting Reinforcement Learning Model Behavior via Koopman with Control
- A Unified Phase-native Computational Principle Governs Hippocampal Spike Timing and Neural Coding
- Accurate Open-Loop Control of a Soft Continuum Robot Through Visually Learned Latent Representations
- GeoLAN: Geometric Learning of Latent Explanatory Directions in Large Language Models
- CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs
- Interpreting the Synchronization Gap: The Hidden Mechanism Inside Diffusion Transformers
- Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning
- Graph-based data-driven discovery of interpretable laws governing corona-induced noise and radio interference for high-voltage transmission lines
- GIP-RAG: An Evidence-Grounded Retrieval-Augmented Framework for Interpretable Gene Interaction and Pathway Impact Analysis
- TRACE: A Multi-Agent System for Autonomous Physical Reasoning in Seismological
- INTRYGUE: Induction-Aware Entropy Gating for Reliable RAG Uncertainty Estimation
- MCLR: Improving Conditional Modeling in Visual Generative Models via Inter-Class Likelihood-Ratio Maximization and Establishing the Equivalence between Classifier-Free Guidance and Alignment Objectives
- Does Mechanistic Interpretability Transfer Across Data Modalities? A Cross-Domain Causal Circuit Analysis of Variational Autoencoders
- Fair splits flip the leaderboard: CHANRG reveals limited generalization in RNA secondary-structure prediction
- Whether, Not Which: Mechanistic Interpretability Reveals Dissociable Affect Reception and Emotion Categorization in LLMs
- Symbolic--KAN: Kolmogorov-Arnold Networks with Discrete Symbolic Structure for Interpretable Learning
- Steering LLMs for Culturally Localized Generation
- SafeSeek: Universal Attribution of Safety Circuits in Language Models
- Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models
- Closing the Confidence-Faithfulness Gap in Large Language Models
- Mechanistically Interpreting Compression in Vision-Language Models
- TRACE: A Multi-Agent System for Autonomous Physical Reasoning for Seismology
- Identifying Connectivity Distributions from Neural Dynamics Using Flows
- Entanglement as Memory: Mechanistic Interpretability of Quantum Language Models
- Sparse Auto-Encoders and Holism about Large Language Models
- EVA: Bridging Performance and Human Alignment in Hard-Attention Vision Models for Image Classification
- Steering Sparse Autoencoder Latents to Control Dynamic Head Pruning in Vision Transformers (Student Abstract)
- Tracking Equivalent Mechanistic Interpretations Across Neural Networks
- BIOGEN: Evidence-Grounded Multi-Agent Reasoning Framework for Transcriptomic Interpretation in Antimicrobial Resistance
- Detecting low left ventricular ejection fraction from ECG using an interpretable and scalable predictor-driven framework
- Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation
- Low-Rank Adaptation Reduces Catastrophic Forgetting in Sequential Transformer Encoder Fine-Tuning: Controlled Empirical Evidence and Frozen-Backbone Representation Probes
- Analytical characterisation of the Mi- and To-phases in HeMiTo dynamics: exponential growth and logistic saturation of toxic prion-like proteins
- From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks
- Thinking Wrong in Silence: Backdoor Attacks on Continuous Latent Reasoning
- Spatiotemporal Characterization of Overdose Mortality in Georgia, USA Using Spectral and Nonlinear Interaction Analysis, 2003-2021
- Identifying and Estimating Causal Direct Effects Under Unmeasured Confounding
- Finding Belief Geometries with Sparse Autoencoders
- Revealing the Learning Dynamics of Long-Context Continual Pre-training
- Do Audio-Visual Large Language Models Really See and Hear?
- A Multi-Level Causal Intervention Framework for Mechanistic Interpretability in Variational Autoencoders
- Automated Attention Pattern Discovery at Scale in Large Language Models
- Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs
- Feature-Aware Anisotropic Local Differential Privacy for Utility-Preserving Graph Representation Learning in Metal Additive Manufacturing
- Learning continuous state of charge dependent thermal decomposition kinetics for Li-ion cathodes using Kolmogorov-Arnold Chemical Reaction Neural Networks (KA-CRNNs)
- ConceptTracer: Interactive Analysis of Concept Saliency and Selectivity in Neural Representations
- The Mechanistic Invariance Test: Genomic Language Models Fail to Learn Positional Regulatory Logic
- Improving Robustness In Sparse Autoencoders via Masked Regularization
- LAG-XAI: A Lie-Inspired Affine Geometric Framework for Interpretable Paraphrasing in Transformer Latent Spaces
- Disentangling MLP Neuron Weights in Vocabulary Space
- Spectral Edge Dynamics Reveal Functional Modes of Learning
- SALLIE: Safeguarding Against Latent Language & Image Exploits
- MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives
- Towards Rapid Constitutive Model Discovery from Multi-Modal Data: Physics Augmented Finite Element Model Updating (paFEMU)
- Transferable FB-GNN-MBE Framework for Potential Energy Surfaces: Data-Adaptive Transfer Learning in Deep Learned Many-Body Expansion Theory
- Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics
- Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?
- Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
- CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models
- The Myth of Expert Specialization in MoEs: Why Routing Reflects Geometry, Not Necessarily Domain Expertise
- Interpretable Relational Inference with LLM-Guided Symbolic Dynamics Modeling
- Causal Drawbridges: Characterizing Gradient Blocking of Syntactic Islands in Transformer LMs
- Weight Patching: Toward Source-Level Mechanistic Localization in LLMs
- CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations
- Mechanistic Decoding of Cognitive Constructs in LLMs
- Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers
- LLM Reasoning Is Latent, Not the Chain of Thought
- The Topological Dual of a Dataset: A Logic-to-Topology Encoding for AlphaGeometry-Style Data
- Where is the Mind? Persona Vectors and LLM Individuation
- Applications of deep generative models to DNA reaction kinetics and to cryogenic electron microscopy
- Surgical Repair of Insecure Code Generation in LLMs
- DLCM: a versatile multi-level solver for heterogeneous multicellular systems
- Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models
- MDAgent: A Multi-Agent Framework for End-to-End Molecular Dynamics Research
- Mechanistic Interpretability Tool for AI Weather Models
- Mechanistic Decoding of Cognitive Constructs in Large Language Models
- Large Language Models Meet Biomedical Knowledge Graphs for Mechanistically Grounded Therapeutic Prioritization
- Directional Confusions Reveal Divergent Inductive Biases Through Rate-Distortion Geometry in Human and Machine Vision
- Locating acts of mechanistic reasoning in student team conversations with mechanistic machine learning
- There Will Be a Scientific Theory of Deep Learning
- Beyond Land Surface Temperature: Explainable Spatial Machine Learning Reveals Urban Morphology Effects on Human-Centric Heat Stress
- Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
- A systematic evaluation of vision-language models for observational astronomical reasoning tasks
- Amplified Urban Climate Extremes from Global Warming-Urbanization Synergy: Toward a Physics-Informed Intelligence Paradigm
- Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer
- Test of Time: Rethinking Temporal Signal of Benchmark Contamination
- AIPsy-Affect: A Keyword-Free Clinical Stimulus Battery for Mechanistic Interpretability of Emotion in Language Models
- VAMP-Net: An Interpretable Multi-Path Network of Genomic Permutation-Invariant Set Attention and Quality-Aware 1D-CNN for MTB Drug Resistance
- DeepImagine: Learning Biomedical Reasoning via Successive Counterfactual Imagining
- From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models
- Learning biophysical models of gene regulation with probability flow matching
- Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models
- Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate
- Rare but Resilient: Dispersal diversity buffers species vulnerability
- reward-lens: A Mechanistic Interpretability Library for Reward Models
- Amplified Urban Climate Extremes from Global Warming-Urbanization Synergy: A Physics-Informed Intelligence Paradigm
- From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models
- Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models
- Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction
- Automated Interpretability and Feature Discovery in Language Models with Agents
- Constructing Interpretable Features from Compositional Neuron Groups
- Barren Plateaus as Destructive Interference: A Diagnostic Framework and Implications for Structured Ansatzes
- Sampled-data Robust Control of Electrically Stimulated Engineered Cell Factories
- Modelling the electrophysiological interactions between human pluripotent cell-derived cardiomyocite grafts and host ventricular tissue
- Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability
- Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation
- How Language Models Process Negation
- Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs
- Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
- A process-based dynamic occupancy model to study range dynamics under non-equilibrium conditions
- Crafting Reversible SFT Behaviors in Large Language Models
- SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders
- From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features
- Patch-Effect Graph Kernels for LLM Interpretability
- SMolLM: Small Language Models Learn Small Molecular Grammar
- Higher-order interactions in ecology can be hidden in plain sight
- Playing the network backward: A Game Theoretic Attribution Framework
- Time series saliency maps: explaining models across multiple domains
- Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training
- Resolving the bias-precision paradox with stochastic causal representation learning for personalized medicine
- Temporal Functional Circuits: From Spline Plots to Faithful Explanations in KAN Forecasting
- Negative Before Positive: Asymmetric Valence Processing in Large Language Models
- Position: Mechanistic Interpretability Must Disclose Identification Assumptions for Causal Claims
- Jagged AI in Scientific Peer Review: Evidence from POMP Data Analysis
- Distributional simplicity bias and effective convexity in Energy Based Models
- PPI-Net connects molecular protein interactions to functional processes in disease
- Supervised sparse auto-encoders for interpretable and compositional representations
- Mean-Pooled Cosine Similarity is Not Length-Invariant: Theory and Cross-Domain Evidence for a Length-Invariant Alternative
- Activation Differences Reveal Backdoors: A Comparison of SAE Architectures
- Generative Modeling with Flux Matching
- Emergent Manifold Separability during Reasoning in Large Language Models
- Essential Role of Extrinsic Noise in Models of E. coli Division Control
- PLOT: Progressive Localization via Optimal Transport in Neural Causal Abstraction
- Beyond the Black Box: Interpretability of Agentic AI Tool Use
- The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts
- Estimating Consensus Epidemic Trajectories via a Constrained Power Fréchet Mean with Functional Registration
- From Syntax to Semantics: Unveiling the Emergence of Chirality in SMILES Translation Models
- Dissecting Jet-Tagger Through Mechanistic Interpretability
- Hidden Error Awareness in Chain-of-Thought Reasoning: The Signal Is Diagnostic, Not Causal
- The Wittgensteinian Representation Hypothesis: Is Language the Attractor of Multimodal Convergence?
- SMIXAE: Towards Unsupervised Manifold Discovery in Language Models
- Data-driven Circuit Discovery for Interpretability of Language Models
- Investigating Anisotropy in Visual Grounding under Controlled Counterfactual Perturbations
- From Mechanistic to Compositional Interpretability
- Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off
- Architecture, Not Scale: Circuit Localization in Large Language Models
- Causal Dimensionality of Transformer Representations: Measurement, Scaling, and Layer Structure
- Hidden Heroes and Gradient Bloats: Layer-Wise Redundancy Inverts Attribution in Transformers
- Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression
- Hiding in Plain Sight: Detectability-Aware Antidistillation of Reasoning Models
- Belief or Circuitry? Causal Evidence for In-Context Graph Learning
- Machine learning the non-radiative decay modes in photochemical processes
- How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits
- LLM Advertisement based on Neuron Auctions
- What Cohort INRs Encode and Where to Freeze Them
- GKnow: Measuring the Entanglement of Gender Bias and Factual Gender
- Mechanistic Interpretability of ASR models using Sparse Autoencoders
- Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
- Native Explainability for Bayesian Confidence Propagation Neural Networks: A Framework for Trusted Brain-Like AI
- bViT: Investigating Single-Block Recurrence in Vision Transformers for Image Recognition
- The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime
- Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
- Dual-Pathway Circuits of Object Hallucination in Vision-Language Models
- All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs
- OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting
- When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability
- Understanding Imbalanced Forgetting in Rehearsal-Based Class-Incremental Learning
- The Rate-Distortion-Polysemanticity Tradeoff in SAEs
- Exploring Geographic Relative Space in Large Language Models through Activation Patching
- Exemplar Partitioning for Mechanistic Interpretability
- Finding Interpretable Prompt-Specific Circuits in Language Models
- Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity
- Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
- XAI and Statistical Analysis for Reliable Intrusion Detection in the UAVIDS-2025 Dataset: From Tree to Hybrid and Tabular DNN Ensembles
- Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models
- Multi-Turn Neural Transparency: Surfacing Neural Activations Improves User Calibration to LLM Behavioral Drift
- Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling
- StructLens: A Structural Lens for Language Models via Maximum Spanning Trees
- Toy Combinatorial Interpretability Models Reveal Lottery Tickets in Early Feature Space
- A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint Principle
- Beyond Linear Superposition: Discovering Climate Features in AI Weather Models with KAN-SAE
- Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies
- HYVINT: Intensity-Driven Hypergraph Generation with Variational Representations
- Sensitivity analysis-guided model reduction of a mathematical model of pembrolizumab therapy for de novo metastatic MSI-H/dMMR colorectal cancer
- Mechanistically Interpretable Neural Encoding Reveals Fine-Grained Functional Selectivity in Human Visual Cortex
- Where Does Authorship Signal Emerge in Encoder-Based Language Models?
- Mechanisms of Object Localization in Vision-Language Models
- Symmetry Matters: Auditing and Symmetrizing 3D Generative Models
- Transformers Linearly Represent Highly Structured World Models
- Lost and Found in Translation: Variational Diagnostics for Neural Codebook Channels
- Post-Hoc Understanding of Metaphor Processing in Decoder-Only Language Models via Conditional Scale Entropy
- From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach
- A Sharper Picture of Generalization in Transformers
- Multi-Modal Machine Learning for Population- and Subject-Specific lncRNA-Type 2 Diabetes Association Analysis
- Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System
- Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs
- Mechanisms of Misgeneralization in Physical Sequence Modeling
- LEAP: A closed-loop framework for perovskite precursor additive discovery
- Reading Task Failure Off the Activations: A Sparse-Feature Audit of GPT-2 Small on Indirect Object Identification
- Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
- Drivers of Transient Dynamics and Persistence in Dengue: Insights from Sensitivity and Stochastic Modeling
- A Mechanistic Explanatory Strategy for XAI
- Protein Thoughts: Interpretable Reasoning with Tree of Thoughts and Embedding-Space Flow Matching for Protein-Protein Interaction Discovery
- Every Component is a Lookup: Token Attribution and Composition from a Single Decomposition
- Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection
- Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography
- Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
- From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Data
- Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy
- Is Inference Mediated by Distinct Semantic Structures in LLMs? A Mechanistic Interpretation
- Continuous-Depth Field Theory for Transformer Patching and Mechanistic Interpretability
- Explainable Retinal Imaging for Prediction of Multi-Organ Dysfunction in Type 2 Diabetes
- The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth
- Investigating the Effect of Network Pruning on Performance and Interpretability
- Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Transformer to Pythia-70m
- Learning dynamical systems with biochemically informed neural ordinary differential equations
- Towards Verifiable Transformers: Solver-Checkable Circuit Explanations
- Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
- Can Broad Biomedical Knowledge be Contextualized into Scenario-Grounded Propositions?
- Emergent Causal-Geometric Dynamics Across Depth in Large Language Models
- SL-BiLEM: Structured Learnable Behavior-in-the-Loop Epidemic Modeling for Forecasting and Policy Evaluation
- CART Random Forests as Sequential Allocation over Random Opportunity Sets: A Stochastic-Control Theory of Ensemble Risk
- MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability
- Stance Detection in Prediction Markets: Addressing Imbalanced Trader Commentary via Counterfactual Augmentation and Market Context
- Determinants of Phase-Separation Propensities, Material States, and Material Properties of Biomolecular Condensates
- Cultural Binding Heads in Language Models
- Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training
- Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs
- Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models
- The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models
- What drives performance in molecular MPNNs? An operator-level factorial benchmark
- Dissecting the Black Box: Circuit-Level Analysis of LLM Vulnerability Detection
- Xetrieval: Mechanistically Explaining Dense Retrieval
- The Curse of Helpfulness: Inverse Scaling Law in Robustness to Distractor Instructions via DistractionIF
- Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge
- Feature Geometry of LoRA Adapters: A Sparse Autoencoder Analysis of Representational Divergence in Fine-Tuned Language Models
- Positional versus Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length Generalization
- Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation
- TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery
- CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware Alignment
- A Bayesian Framework for Uncertainty-Aware Estimation of Main Pulmonary Artery Velocity Profiles from Phase-Contrast MRI
- Ubiquity of Emergent Hebbian Dynamics in Regularized Learning
- Discovering a Zeta Map Algorithm on Dyck Paths via Mechanistic Interpretability
- Translation Heads: Disentangling meaning from language in LLM-based machine translation
- Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States
- A Monosemantic Attribution Framework for Stable Interpretability in Clinical Neuroscience Transformer-Based Language Models
- When Do Attention Circuits Form? Developmental Trajectories of Capability and Attention-Sink Emergence Across Three 1B-ClassArchitectures
- Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation
- Matter to Mechanism: A Benchmark for AI Co-Scientists in Materials and Battery Research
- Ablating Archetypes: The Stability of Archetypal SAEs is an Artifact of Initialization and Metric Design
- Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning
- From Performance to Viability: A Bootstrap Framework for Latent-Space Representation Learning in Adaptive Biological Systems
- Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention
- A literature-grounded scientific reasoning framework for defect-engineered TiO_{2}_{2} photocatalysts
- Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning
- Detection vs. Execution: Single-Bucket Probes Miss Half the Mamba-2 State Sink
- Positional Encodings Anchor Spatial Structure in Vision Transformers: A Geometric Perspective on Robustness
- Closed-Loop Molecular Design with Calibrated Deference
- Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability
- Unsupervised Pattern Analysis in Japanese Veterinary Toxicology: A Regulatory-Compliant Framework for Cross-Species Risk Assessment
- Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programming
- Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads
- Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers
- Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics
- Wearable Single-Lead ECG Detects Fine-Grained Structural Heart Disease Through Echo-Report Supervision
- Trajectory Geometry of Transformer Representations Across Layers
- Sycophancy Towards Researchers Drives Performative Misalignment
- Ablation-Reversible Heads Don't Transfer: A Stress Test for Mechanistic Role Claims in Transformers
- GPT-Micro: A large language paradigm for accelerated, inexpensive, and thermodynamics-consistent discovery of constitutive models in manufacturing
- Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms
- Biological Reasoning-Informed Regression for Interpretable Regulatory DNA Activity Prediction
- TianJi-Environ: An Autonomous AI Scientist for Atmospheric Environmental Research
- Contribution Weights: A Geometrical Analysis of Self-Attention Transformers
- DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression
- LLM-Mediated Demand Response Coordination in Smart Microgrids
- VFUSE: Virulent Feature Understanding with Sparse autoEncoders
- Interactions Between Crosscoder Features: A Compact Proofs Perspective
- When Attribution Patching Lies: Diagnosis and a Second-Order Correction
- ATLAS: Active Theory Learning for Automated Science
- The Standard Interpretable Model: A general theory of interpretable machine learning to deductively design interpretable methods using Lagrangian mechanics
- Interpretable enzyme function prediction via sparse autoencoder features of ESMC across the microbial protein universe
- Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics
- Impact of Oxygen on DNA Damage Distribution in 3D Genome and its Correlation to Oxygen Enhancement Ratio after High-LET Irradiation
- Transformer Field Theory: A Response-Theoretic Approach to Mechanistic Interpretability
- Layer-Resolved Optimal Transport for Hallucination Detection in NMT and Abstractive Summarization
- Understanding helpfulness and harmless tension in reward models
- When Does Routing Become Interpretable? Causal Probes on Block Attention Residuals
- Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning
- On Pitfalls of \textit{RemOve-And-Retrain}\textit{RemOve-And-Retrain}: Data Processing Inequality Perspective
- Bag of Dims: Training-Free Mechanistic Interpretability via Dimension-Level Sign Patterns
- Scalable Circuit Learning for Interpreting Large Language Models
- Demystifying Variance in Circuit Discovery of LLMs
- Factorized Neural Operators Decompose Dynamic and Persistent Responses
- Learning Hybrid Biophysical Neuron Models with Neural ODEs
- Circuit Tracing in Autoregressive Protein Language Models
- DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing
- HAPI-EP: Towards Hybrid, Adaptive, and Predictive Digital Twins of Cardiac Electrophysiology
- Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning
- Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
- Size Doesn't Matter: Cosine-Scored Sparse Autoencoders
- Transformers Learn the Mestre-Nagao Heuristic
- Rational Sparse Autoencoder
- Compressed Computation is (probably) not Computation in Superposition
- A Low-Rank Subspace Analysis of LLM Interventions
- Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions
- Ten Years of the Stochastic Resonance Model of Tinnitus: From Phantom Perception to Adaptive Sensory Optimization
- The Discrete-Log Clock: How a Transformer Learns Modular Multiplication
- Diagnosing and Repairing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry
- OrthoReg: Orthogonal Regularization for Hybrid Symbolic-Neural Dynamical Systems
- Who Wins the Conflict? Mechanistic Interpretability of Text Bias in Audio LLMs
- Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generation
- Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment
- The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs
- Effects of sparsity and superposition on loss in simple autoencoders
- Beyond AHI: An Interpretable Causal-Discovery-Guided Framework for Sleep Recovery in Connected Health
- Critical Percolation as a Synthetic Data Model for Interpretability
- Decoding the Alzheimer's Continuum: Interpretable Multi-Gate Routing for Diagnosis and Transition Prediction
- Multimodal Concept Bottleneck Models
- Residue-Level Attributions in Protein Language Models Do Not Recover Allergen Epitopes
- Sparse Neuron Ablation Triggers Catastrophic Collapse of the Language Core in Large Vision-Language Models
- Local Causal Attribution of Chain-of-Thought Reasoning
- Beyond Hooking Onto the World: Referential Profiles and the Numerical Structure of LLM Grounding
- A Validation-Gated Mechanistic Account of Suicidality Detection in LLMs
- BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery
- Beyond Importance: Interchange-Sobol Sensitivity Reveals Task-Specific Content Channels in Transformer Components
- DeepBD: A Grounded Agentic Workflow for Variant Prioritization and Diagnosis of Genetic Birth Defects
- The mechanics of anisotropic active plates with applications to cell alignment on curved substrates
- Towards Version-aware Operations and Transaction Memories for Multi-layer MeMo
- Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?
- Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators
- A Reduced Order Model for Emergent Mechanics in Woven Systems
- Emergent Relational Order in LLM Agent Societies: From Collective Affect to Authority Stratification
- AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent
- Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models
- LMs as Task-Specific Knowledge Bases: An Interpretability Analysis
- Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders
- Radical AI Interpretability
- Localizing RL-Induced Tool Use to a Single Crosscoder Feature
- Refusal Lives Downstream of Persona in Chat Models
- Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA
- The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching
- PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding
- Structural functional identifiability and model discovery in differential equation models
- EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures
- How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
- Representational Depth of Evaluation Awareness Shifts With Scale in Open-Weight Language Models
- Symbolic Mechanistic Data Attribution: Tracing Training Influence to Learned Behavioral Policies
- Attribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning
- Mechanistic Personality Analysis of LLMs Steering Personality via Latent Feature Interventions
- Sparse Autoencoders are Capable LLM Jailbreak Mitigators
- Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?
- Deductive Logic in Language Models: Horizontal vs Vertical Reasoning
- Deep Indentation of Hyperelastic Materials Reveals Tip Independent Parabolic Force Depth Response via Strain Energy Delocalization
- An Interaction Language Model: Mechanism Discovery from Statistical Patterns of Physical Interactions
- A Mechanistic Study of Transformers Training Dynamics
- Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation
- Muon as a Residual Connection
- LLM-Guided ODE Discovery and Parameter Inference from Small-Cohort Aggregate Data
- Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol
- Towards Robustness against Typographic Attack with Training-free Concept Localization
- Fast Multi-dimensional Refusal Subspaces via RFM-AGOP
- Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits
- Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability
- Identifiability Limits of Physics-Informed Inference for Spatial Stochastic Dynamics from Static Snapshots
- From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents
- Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders
- Predicting Therapeutic Outcome via Aligning Patient-Specific Knowledge Graph and Gene-Level Perturbation Representations
- Geometry of Ordinal Representations in Language Models
- Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models
- Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources
- Individual Parameters in Weight-Sparse Transformers Appear Interpretable
- MatPhaseBench: A Semantics-Guided Benchmark for Materials Phase Diagrams Understanding
- Induction Heads Interpolate N-Grams
- Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders
- Latent Programming Horizons in Coding Agents
- Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
- How Learning Dynamics Drive Adversarially Robust Generalization?
- Reliable mechanistic operator recovery with biologically-informed neural networks: principles for architecture and optimisation design
- Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning
- From Statistical to Structural Synergy: A Predictability Framework to Quantify the Effects due to High-Order Mechanisms
- Multiplication Beyond Groups: Stratified Fourier Mechanisms in Transformer Circuits
- Dissociating the Internal Representations of Sycophancy in LLMs
- When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities
- Cross-seed explainability using Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoders
- The impact of nonheritable variation in division rates on population growth across environments
- Towards Isolated Interventions via Almost Orthogonal Features in Language Models
- Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability
- Before the Last Token: Diagnosing Final-Token Safety Probe Failures
- Diagnosing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry
- Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs
- Temporal Preference Concepts and their Functions in a Large Language Model
- Which Neurons Detect Malicious Code? A Probing Study of LLM Security Knowledge
- MLPs are Hebbians: Constructing Efficient Fact-Storing MLPs for Transformers
- Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across Scale
- From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery
- Same Compression Principle, Different Geometry: Rate-Distortion Signatures Dissociate Biological and Artificial Visual Systems
- Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias
- Observable Performance Does Not Fully Reflect Adaptive System Organization: A Multi-Level Analysis of Gait Dynamics Under Occlusal Constraint
- AI-Augmented Adaptive Digital Twin Modeling for Brain Tumor Evolution Prediction and Treatment Scheduling
- The Refusal Residue: When Probes Catch Alignment Faking and When They Don't
- RTS Smoother-Guided Learning of Physics-Based Neural Differential Models
- Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control
- Transcoders for Investigating Deception in Language Models
- Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions
- Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models
- Language Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models
- Compartmental Disease Models with Time-Varying Transmission Rates: A Bayesian Generalized Hamiltonian Monte Carlo framework with Applications to COVID-19
- Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence
- Dispersal diversity buffers species vulnerability to local extinction
- What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle Learning
- Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMs
- Can Interpretation Predict Behavior on Unseen Data?
- Emergent Hierarchical Monosemantic Neurons from the Group-Contrastive Forward-Forward Algorithm
- CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability
- Spatially resolved in-situ characterisation of competing martensitic transformation pathways during nanoscratch in 316H Stainless Steel
- Interval and fuzzy physics-augmented neural networks (iPANN and fPANN) for uncertainty quantification and propagation in constitutive modeling
- A Hybrid Framework for Uncertainty Quantification in Partially Observed Dynamic Biological Systems
- OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization
- Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers
- From Noise to Diversity: Random Embedding Injection in LLM Reasoning
- Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry
- What Does Chain-of-Thought Contribute at Probe Time? Evidence for Local Co-Occurrence Activation
- A Mechanistic Perspective and Circuit-Guided Difficulty Metric for Unlearning
- Do LLMs Know Their Vulnerable Scenarios?
- Continuous surrogates versus threshold Boolean networks for modeling Arabidopsis ISR gene regulation
- Inverse Bayesian Inference for Extracting Lesion Dynamics from Longitudinal Spectral CT
- Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models
- Emergent Symbolic Structure in Health Foundation Models: Extraction, Alignment, and Cross-Modal Transfer
- Phase Structure in Rotary Attention: A Spectral Framework for Semantic Continuity and Execution-Boundary Governance
- Emergent Latent-State Computation under Stochastic Volatility
- Beyond the Post Hoc User Study: Modeling Visual Decision-Making with Active Inference
- A Hierarchical Validity-Audit Framework for Neural Mass Models in Simulation-Based Inference: From Observational Coverage to Mechanistic Interpretation
- Can We Trust AI in 6G? Verifiable and Auditable AI-Driven Trustworthy Wireless Networks
- HYVINT: Intensity-Driven Hypergraph Generation with Variational Embeddings
- Information Processing by Neuron Populations in the Central Nervous System: A Theory of the Mathematical Structure of Data and Operations
- Generic Vision and Cross-Attention for Reaction Yield Prediction
- DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning
- Mechanistic bridges from receptors to whole-brain dynamics: mean-field reductions, validity domains, and computational trade-offs
- A Conductance Based Amygdala Model of Threat Processing in Anxiety and Depression
- The production of meaning in the processing of natural language
- Real-time dynamics of the two-step charge-density-wave transition in bulk 1T-TaS_2_2
- Cardiovascular Digital Twins from Physics Based to Data Driven Approaches
- Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models
- Wigner's Friend Paradox Revisited
- LLMs Can Annotate Attribution Graphs
- Sparse Weight Decomposition for Efficient Circuit Extraction
- Curriculum Multiple Shooting for Robust Training of Neural and Universal Differential Equations
- Subliminal Learning is Non-Semantic Distillation
- Transformers Struggle to Use Their Emergent World Models: Revisiting the Tower of Hanoi, and the Illusion of Thinking
- Finding Usable Weight Mechanisms with Tiled SVD
- Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric Data
- MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering
- Can Graph Learning Learn Circuits?
- Control-Diverse Reinforcement Fine-Tuning: Decoupling the Shared Control Bottleneck of RL Post-Training
- Mechanistic Interpretability-Guided Selective Fine-Tuning of Vision-Language Models for Centimeter-Level Flood Depth Estimation
- Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability
- Decoding Transient X-ray Absorption Spectra of Acetylacetone With Multireference Algebraic Diagrammatic Construction Theory
- From Rating Factors to Crash Mechanisms: A Multiscale Causal DAG Framework Linking Motor Insurance and Road Safety
- Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways
- Label-Free Parkinson's Disease Screening from Face and Voice through Mechanistic Interpretability
- Explainability in Practice: A Survey of Explainable NLP Across Various Domains
- Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
- From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop
- Observable-Reduction-Guided Sparse Regression for Partially Observed Active-Quiescent Systems
- Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia
- Decoding Task Progress from VLA Representations
- Data-Efficient and Interpretable Classification of Circulating Tumor Cell Phenotypes in Microfluidic Devices via Deep Learning
- SCOUT: Semantic Concept Discovery for Open-Vocabulary Editing of face Recognition Templates
- Protein Structure Prediction: From Evolutionary Constraints to Generative Modeling
- CulTrace: Tracing Internal Cultural Reasoning in Large Language Models
- Not All Attention Is Equal: A Quantitative Survey of the EEI Trade-off
- DA-RAC: Distance-Aware Calibration of LLM Judges for Trustworthy AI Auditing
- SpIn-ViT: Designing a Sparsity-Induced Vision Transformer That Is Mechanistically Interpretable
- A Tale of Two Pathways to Gompertz Mortality: Reliability and Vitality from an Actuarial Perspective
- Structure-Guided Spatiotemporal Attention Graph Neural Network for Traffic Flow Prediction
- NAST: Improving Negation Handling in Medical Vision-Language Models through Negation-Aware Selective Training
- SPEAR: Structure Property Explainability with Attention Regularization
- Explanation Multiplicity: Circuit-Level Interpretability Evidence Does Not Survive Defensible Analytic Variation
- Inferring Mechanisms from Bits: Promises and Pitfalls of Higher-Order Information in Cognitive Science
- Mechanistic Interpretability of Structure-Aware Numerical Reasoning in LLaMA 3.1 8B
- Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability
- Explaining Intrinsic Moral Self-Correction with Mechanistic Interpretability
- The Intrinsic Dimension of Prompts in Internal Representations of Large Language Models
- Structure is information: structural identifiability mappings for machine learning with partially observed dynamical systems
- Deep Learning Models Also Recall Features
- Bridging Linguistic Structure and Mechanistic Interpretability for Conceptual Interpretation in Language Models
- Grounding Isn't Knowing: Do VLMs Need Object Localization for Spatial Reasoning?
- What AstroPT knows about galaxies, and what that can teach us about LLMs
- Mechanistic Interpretability of Chain-of-Thought Reasoning via Sequential Activation Patching
- Why Does Robustness Reduce Superposition?
- Align, Unify, Suppress, Route: A Coherentist View of Transformer Computation
- The Communication Map of a Transformer
- Finding and using interpretable latents in a neutrino foundation model with sparse autoencoders
- Direct current thermo-mechanical testing: Principles, uncertainty hierarchy, and its role in advanced materials characterisation
- RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons
- Beyond Static Interpretability: Anticipating Post-SFT Mechanisms from Pre-SFT Parameters for Better Tuning
- A Circuit, Not The Circuit: Non-Unique Causal Localisation of the Mamba-2 State Sink
- Mechanistic Circuit Identification for Controllable Data Generation
- Discovering Cross-Language Reasoning Invariance in LLMs with Geometry-Invariant Sparse Autoencoders
- Modality Contribution Score - A Per-Patient Framework for Quantifying the Relative Diagnostic Contribution of Structural MRI and Amyloid PET in Alzheimer's Disease
- Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation
- Not All Eval-Awareness Is Equal: Capabilities Framing Predicts Compliance
- Circuit Condensation: Post-Training that Concentrates a Behavior's Causal Circuit
- Interpreting Latent Protein Language Model Features with Geometric Annotations
- Mode-Specific Dynamics of CO2 Hydrogenation on Copper: The Hidden Role of Molecular Rotation
- Compositional Failure in Audio-Visual LLMs: Late-Layer Prior Dominance Under Cross-modal Conflict
- Load-Bearing Context: The Question Damage Score for Evaluating Context Reliance in Linguistic Reasoning
- Probing Perceptual Priors of MLLMs via Gibbs Sampling with Interpretable Generative Controls
- How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution
- Circuit Discovery Helps Detect LLM Jailbreaking: A Mechanistic Interpretability Study
- Tracing the Latent Threads: A Mechanistic Study of How LLMs Represent and Operationalize Race and Ethnicity Cues
- MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines
- The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal
- Why Are LLM Backdoor Defenses Fragmented? A Feature-Level Explanation with Sparse Autoencoders
- Interpreting and Steering for Safe and Correct Code Generation
- When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs
- Sparse Koopman Autoencoders Identify Local Dynamical Regimes in Multibasin Systems
- A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability
- Causal Interventions Reveal Typologically Organized Syntactic Mechanisms in Multilingual Language Models
- SNF-Bench: Separating Static Drift from Natural Flow in Long-Horizon Fixed-Camera Video Generation
- Pressure-regulated mechanochemistry at lithium metal-sulfide electrolyte interfaces
- S^3martCirc: Self-supervised Smart Circuit Discovery
- From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling
- Interpretable Symptom Vectors for Depression in a Large Language Model
- A mechanistic modeling framework to interpret ACTH stimulation tests across HPA axis adaptation states and glucocorticoid feedback dynamics
- A Circuit for Plural Reference: How LLMs Represent and Retrieve Singular and Plural Entities
- Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving Perturbations
- Large Language Models in Resolving Contextual Knowledge Conflicts
- The Gradient Does Not See Rank: Rank-Indifference in Matrix-CODI on ProsQA
- ObserverBench: Testing Mechanistic Estimates for Intervention and Control
- Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs
- On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing
- PhysSAE: Mechanistic Interpretability with Sparse Autoencoders
- DrugReason: Dynamic Multi-View Reasoning over Knowledge Graph and Language Evidence for Drug Repurposing
- When Does Activation Steering Change What a Model Computes From?
- Covariance Spectrum in Nonlinear Recurrent Neural Networks: A Near-Critical Effective Connection Strength Throughout Chaos
- Capsule Lens: Locating and Tracking Concept Geometry in Model Representations
- SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
- Noise in Diffusion Models Is a Learnable Input
- Medical AI Encodes a "Feeling of Error": Verifying Cancer Segmentation via Internal Concepts
- Autonomous Chemical Mechanistic Discovery through Agentic Reasoning and Validation
- Mixing dynamics and transport mechanisms during laminar stirring flows
- Sparse Weight and Edge Circuit Discovery in Transformer-based Acoustic Models
- Operator-matched spatial regression
- The Misery of Mechanistic Interpretability: A Formal Perspective
- Artificial entrepreneurial cognition: Locating and causally steering an opportunity recognition dial inside large language models (LLMs)
- Sensory Precision Inference for Multimodal Arbitration under Uncertainty
- What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE Track
- PhysSAE: Mechanistic Interpretability of PINNs with Sparse Autoencoders
- Domain-Specific Jargon in Large Language Models: A Comparative Analysis between General-Purpose and Specialist Models
- Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models
- (How) Do MLLMs Report Bistable Images Like Humans?
- There Is More to Refusal in Large Language Models than a Single Direction
- Flag Game: A Toy Model for Mechanistic Swarm Interpretability
- A Four-Stage Decomposition of Word-Problem Solving and Mechanistic Fragility in LLM Math Reasoning
- Reproducing Transparent and Scrutable Recommendations: Exploring Open-Weight Models via Natural-Language User Profiles
- Enhanced Agriculture-informed Neural Network by Domain Knowledge
- World Modeling in Transformers
- Integral chemical reaction neural networks
- Identifying Neural State Changes due to Gain versus Off-Manifold Displacement
- From In Silico to In Vitro: A Comprehensive Guide to Validating Bioinformatics Findings
- Comparing Latent Concept Formation in State Space Models and Transformers via Sparse Autoencoders
- Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity
- Circuit-Diff: Factual Edit-based Intervention Method for Localizing Knowledge in Attribution Graphs
- Quantitative Classical Relaxation Dynamics of Penning-Ionized He/Ne--H_2^+_2^+/HD^+^+ Complexes
- Machine-Interpretable Information: Compiling Documents into Searchable and Readable Protocol States
- How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation
- Look Before You Steer: Geometry Predicts SAE Feature Steerability
- In Vivo Length Distributions as Mechanistic Fingerprints of Pathological Protein Aggregation
- Quantitative Evidence Mining for Plausibility-Aware Biomedical AI: A Narrative Review and Conceptual Framework
- Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in LLMs
- Learning continuous reaction paths for transition-state prediction
- Matryoshka attribution: Learning to attribute language model outputs to representations and weights
Dedicated Publication Threads
Library
Tutorial
Written Tutorials
- Mechanistic Interpretability for LLMs, explained by The CounterFactual
- Zoom In: An Introduction to Circuits (Bilingual Tutorial) - Bilingual (Chinese/English) hands-on Jupyter notebook tutorial reproducing Olah et al. 2020's circuits research, covering feature visualization and mechanistic interpretability in CNNs.
Video Tutorials
Contributing
We welcome contributions to this repository! If you have a resource that you believe should be included, please submit a pull request or open an issue. Contributions can include:
- New libraries or tools related to mechanistic interpretability
- Tutorials or guides that help users understand and implement mechanistic interpretability techniques
- Research papers that advance the field of mechanistic interpretability
- Any other resources that you find valuable for the community
How to Contribute
- Fork the repository.
- Create a new branch for your changes.
- Make your changes and commit them with a clear message.
- Push your changes to your forked repository.
- Submit a pull request to the main repository.
Before contributing, take a look at the existing resources to avoid duplicates.
License
This repository is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). You are free to share and adapt the material, provided you give appropriate credit, link to the license, and indicate if changes were made.
Star History
llms
mechanistic-interpretability
Contributors
Similar repos
Languages
JavaScript
100.0%
A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on Mechanistic Interpretability, a growing subfield in machine learning interpretability research that aims to reverse-engineer neural networks into understandable computational components.
See the codeREADME
Awesome Mechanistic Interpretability
A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on Mechanistic Interpretability, a growing subfield in machine learning interpretability research that aims to reverse-engineer neural networks into understandable computational components. This repository serves as a comprehensive and well-organized knowledge base for researchers, engineers, and enthusiasts working to uncover the inner workings of modern AI systems, particularly large language models (LLMs).
To ensure that the community stays updated on the latest developments, our repository is automatically updated with recent mechanistic interpretability papers from arXiv. This ensures timely access to new techniques, discoveries, and frameworks that are shaping the future of model transparency and alignment.
[!NOTE] 📢 Announcement: Our paper from AIT Lab is now available on ACM CSUR!
Title: Bridging the Black Box: A Survey on Mechanistic Interpretability in AI
If you find this paper interesting, please consider citing our work. Thank you for your support!
@article{somvanshi2025bridging,
title={Bridging the Black Box: A Survey on Mechanistic Interpretability in AI},
author={Somvanshi, Shriyank and Islam, Md Monzurul and Rafe, Amir and Tusti, Anannya Ghosh and Chakraborty, Arka and Baitullah, Anika and Chowdhury, Tausif Islam and Alnawmasi, Nawaf and Dutta, Anandi and Das, Subasish},
journal={Available at SSRN 5345552},
year={2025}
}
Whether you are investigating the circuits behind in-context learning, decoding attention heads in transformers, or exploring interpretability tools like activation patching and causal tracing, this collection serves as a centralized hub for everything related to Mechanistic Interpretability — enriched by original peer-reviewed contributions and hands-on research from the broader interpretability community.
Updates
- [Feb 04, 2026]: Our paper has been accepted at ACM Computing Surveys 🎉!
- [Jul 24, 2025]: Preprint is now available in SSRN.
Last Updated
September 23, 2026 at 02:55:26 AM UTC
Theorem
Papers (1210)
- Mechanistic Decomposition of Sentence Representations
- Domain Switching on the Pareto Front: Multi-Objective Deep Kernel Learning in Automated Piezoresponse Force Microscopy
- Rethinking Crowd-Sourced Evaluation of Neuron Explanations
- MIB: A Mechanistic Interpretability Benchmark
- Training Superior Sparse Autoencoders for Instruct Models
- RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs
- Performance Gap in Entity Knowledge Extraction Across Modalities in Vision Language Models
- A CRISP approach to QSP: XAI enabling fit-for-purpose models
- Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws
- Tug-of-war between idiom's figurative and literal meanings in LLMs
- TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research
- Evaluating Neuron Explanations: A Unified Framework with Sanity Checks
- A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
- Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective
- The Vector Grounding Problem
- An analytic theory of creativity in convolutional diffusion models
- Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey
- Visualizing and Controlling Cortical Responses Using Voxel-Weighted Activation Maximization
- Is the end of Insight in Sight ?
- Forecasting Seasonal Influenza Epidemics with Physics-Informed Neural Networks
- Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models
- Tracking the Feature Dynamics in LLM Training: A Mechanistic Study
- Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video
- Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning
- Do Large Language Models (Really) Need Statistical Foundations?
- Identifying interactions across brain areas while accounting for individual-neuron dynamics with a Transformer-based variational autoencoder
- SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs
- Anchored Answers: Unravelling Positional Bias in GPT-2's Multiple-Choice Questions
- : Interpreting and leveraging semantic information in diffusion models
- Circuit Stability Characterizes Language Model Generalization
- Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs
- Planning in a recurrent neural network that plays Sokoban
- Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability
- BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model
- Enhancing Automated Interpretability with Output-Centric Feature Descriptions
- Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks
- Sparsification and Reconstruction from the Perspective of Representation Geometry
- Mitigating Overthinking in Large Reasoning Models via Manifold Steering
- Understanding Synthetic Context Extension via Retrieval Heads
- In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention
- MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation
- The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
- Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
- From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance
- Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks
- MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding
- The Birth of Knowledge: Emergent Features across Time, Space, and Scale in Large Language Models
- DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding Spaces
- Multi-Scale Probabilistic Generation Theory: A Hierarchical Framework for Interpreting Large Language Models
- The Origins of Representation Manifolds in Large Language Models
- The Remarkable Robustness of LLMs: Stages of Inference?
- Monet: Mixture of Monosemantic Experts for Transformers
- Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization
- PAL: Probing Audio Encoders via LLMs -- A Study of Information Transfer from Audio Encoders to LLMs
- Revisiting Transformers with Insights from Image Filtering
- Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
- Understanding the Repeat Curse in Large Language Models from a Feature Perspective
- Sectoral Coupling in Linguistic State Space
- SAE-V: Interpreting Multimodal Models for Enhanced Alignment
- Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders
- Interpretability and Generalization Bounds for Learning Spatial Physics
- A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning
- Mechanistic Interpretability in the Presence of Architectural Obfuscation
- Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)
- Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference
- Validating Mechanistic Interpretations: An Axiomatic Approach
- Six Fallacies in Substituting Large Language Models for Human Participants
- Mechanistic Interpretability of Diffusion Models: Circuit-Level Analysis and Causal Validation
- From memories to maps: Mechanisms of in context reinforcement learning in transformers
- Measuring and Guiding Monosemanticity
- Emergent collective dynamics from motile photokinetic organisms
- Mechanistic Interpretability Needs Philosophy
- Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition
- Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
- Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
- Bilinear MLPs enable weight-based mechanistic interpretability
- From Memories to Maps: Mechanisms of In-Context Reinforcement Learning in Transformers
- Amortizing personalization in virtual brain twins
- Stochastic Parameter Decomposition
- Understanding Verbatim Memorization in LLMs Through Circuit Discovery
- Mechanistic Interpretability of Emotion Inference in Large Language Models
- Data-Driven Multiscale Topology Optimization of Spinodoid Architected Materials with Controllable Anisotropy
- SAFER: Probing Safety in Reward Models with Sparse Autoencoder
- Prompting as Scientific Inquiry
- Emerging AI Approaches for Cancer Spatial Omics
- Learning Modular Exponentiation with Transformers
- Constraint-Guided Symbolic Regression for Data-Efficient Kinetic Model Discovery
- Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability
- Circuit-tuning: A Mechanistic Approach for Identifying Parameter Redundancy and Fine-tuning Neural Networks
- Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs
- Scientific Machine Learning of Chaotic Systems Discovers Governing Equations for Neural Populations
- Quantifying Cross-Attention Interaction in Transformers for Interpreting TCR-pMHC Binding
- Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs
- Dynamical Archetype Analysis: Autonomous Computation
- A statistical approach to latent dynamic modeling with differential equations
- The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?
- Mechanistic Indicators of Understanding in Large Language Models
- Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers
- Towards Interpretable Drug-Drug Interaction Prediction: A Graph-Based Approach with Molecular and Network-Level Explanations
- Simulation as Supervision: Mechanistic Pretraining for Scientific Discovery
- A PBN-RL-XAI Framework for Discovering a "Hit-and-Run" Therapeutic Strategy in Melanoma
- Propensity score weighting across counterfactual worlds: longitudinal effects under positivity violations
- Mechanistic Interpretability of LoRA-Adapted Language Models for Nuclear Reactor Safety Applications
- Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning
- CytoSAE: Interpretable Cell Embeddings for Hematology
- FADE: Why Bad Descriptions Happen to Good Features
- Tracing Facts or just Copies? A critical investigation of the Competitions of Mechanisms in Large Language Models
- Teach Old SAEs New Domain Tricks with Boosting
- Insights into a radiology-specialised multimodal large language model with sparse autoencoders
- Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility
- Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
- Understanding Matching Mechanisms in Cross-Encoders
- Decoding Translation-Related Functional Sequences in 5'UTRs Using Interpretable Deep Learning Models
- Probing Ranking LLMs: A Mechanistic Analysis for Information Retrieval
- Deep Learning for Blood-Brain Barrier Permeability Prediction
- Residual Koopman Model Predictive Control for Enhanced Vehicle Dynamics with Small On-Track Data Input
- CircuitProbe: Dissecting Spatiotemporal Visual Semantics with Circuit Tracing
- HumorDB: Can AI understand graphical humor?
- Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
- A nonparametric approach to practical identifiability of nonlinear mixed effects models
- Large Language Models Are Human-Like Internally
- How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation
- Can You Trust an LLM with Your Life-Changing Decision? An Investigation into AI High-Stakes Responses
- Semiclassical Spin Exchange via Temperature-Dependent Transition States
- Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders
- Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes
- How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
- Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning
- Modeling the Temperature-Humidity Coupling Dynamics of Soybean Pod Borer Population and Assessing the Predictive Performance of the PCM-NN Algorithm
- I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
- Covariance spectrum in nonlinear recurrent neural networks
- Discovery of Disease Relationships via Transcriptomic Signature Analysis Powered by Agentic AI
- Evaluating and Designing Sparse Autoencoders by Approximating Quasi-Orthogonality
- Surgical Knowledge Rewrite in Compact LLMs: An 'Unlearn-then-Learn' Strategy with (IA^3IA^3) for Localized Factual Modulation and Catastrophic Forgetting Mitigation
- Activation Steering for Bias Mitigation: An Interpretable Approach to Safer LLMs
- Entangled in Representations: Mechanistic Investigation of Cultural Biases in Large Language Models
- BiasGym: Fantastic Biases and How to Find (and Remove) Them
- From Transformer to Biology: A Hierarchical Model for Attention in Complex Problem-Solving
- How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
- Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders
- BiasGym: Fantastic LLM Biases and How to Find (and Remove) Them
- eDIF: A European Deep Inference Fabric for Remote Interpretability of LLM
- Maximum Entropy Models for Unimodal Time Series: Case Studies of Universe 25 and St. Matthew Island
- Mantis: A Simulation-Grounded Foundation Model for Disease Forecasting
- CALYPSO: Forecasting and Analyzing MRSA Infection Patterns with Community and Healthcare Transmission Dynamics
- Counterfactual Probabilistic Diffusion with Expert Models
- Modeling GRNs with a Probabilistic Categorical Framework
- Disentangling concept semantics via multilingual averaging in Sparse Autoencoders
- LLMSymGuard: A Symbolic Safety Guardrail Framework Leveraging Interpretable Jailbreak Concepts
- From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits
- Fidelity Isn't Accuracy: When Linearly Decodable Functions Fail to Match the Ground Truth
- Beyond Transcription: Mechanistic Interpretability in ASR
- Mechanistic Exploration of Backdoored Large Language Model Attention Patterns
- KL-based self-distillation for large language models
- Adversarial Examples Are Not Bugs, They Are Superposition
- LLM Assertiveness can be Mechanistically Decomposed into Emotional and Logical Components
- Disentangling Polysemantic Neurons with a Null-Calibrated Polysemanticity Index and Causal Patch Interventions
- Rethinking scale in network neuroscience: Contributions and opportunities at the nanoscale
- Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability
- Biologically Disentangled Multi-Omic Modeling Reveals Mechanistic Insights into Pan-Cancer Immunotherapy Resistance
- Tracing Positional Bias in Financial Decision-Making: Mechanistic Insights from Qwen2.5
- Linear Power System Modeling and Analysis Across Wide Operating Ranges: A Hierarchical Neural State-Space Equation Approach
- Even Heads Fix Odd Errors: Mechanistic Discovery and Surgical Repair in Transformer Attention
- RelP: Faithful and Efficient Circuit Discovery via Relevance Patching
- Prompt the Unseen: Evaluating Visual-Language Alignment Beyond Supervision
- Mechanistic interpretability for steering vision-language-action models
- Can LLMs Lie? Investigation beyond Hallucination
- Challenges in Understanding Modality Conflict in Vision-Language Models
- Non-Linear Model-Based Sequential Decision-Making in Agriculture
- Preserving Bilinear Weight Spectra with a Signed and Shrunk Quadratic Activation Function
- Pulling Back the Curtain on ReLU Networks
- Sparse Autoencoder Neural Operators: Model Recovery in Function Spaces
- Personality as a Probe for LLM Evaluation: Method Trade-offs and Downstream Effects
- Interpreting Transformer Architectures as Implicit Multinomial Regression
- ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders
- Towards explainable decision support using hybrid neural models for logistic terminal automation
- Measuring Uncertainty in Transformer Circuits with Effective Information Consistency
- Think-to-Talk or Talk-to-Think? When LLMs Come Up with an Answer in Multi-Hop Arithmetic Reasoning
- Data-driven discovery of dynamical models in biology
- Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors
- The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis
- Interpretability as Alignment: Making Internal Understanding a Design Principle
- Behind the Scenes: Mechanistic Interpretability of LoRA-adapted Whisper for Speech Emotion Recognition
- Decoding the Stability of Transition-Metal Alloys with Theory-infused Deep Learning
- An Agentic AI Workflow to Simplify Parameter Estimation of Complex Differential Equation Systems
- Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal
- The power of dynamic causality in observer-based design for soft sensor applications
- Modelling Under-Reported Data: Pitfalls of Naïve Approaches and a New Statistical Framework for Epidemic Curve Reconstruction
- The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features
- Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content
- Swarm Intelligence for Chemical Reaction Optimisation
- Unified Spatiotemopral Physics-Informed Learning (USPIL): A Framework for Modeling Complex Predator-Prey Dynamics
- Learning Mechanistic Subtypes of Neurodegeneration with a Physics-Informed Variational Autoencoder Mixture Model
- Unified Spatiotemporal Physics-Informed Learning (USPIL): A Framework for Modeling Complex Predator-Prey Dynamics
- Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models
- DeepMech: A Machine Learning Framework for Chemical Reaction Mechanism Prediction
- Modeling Transformers as complex networks to analyze learning dynamics
- Bayesian Calibration and Model Assessment of Cell Migration Dynamics with Surrogate Model Integration
- Learning From Simulators: A Theory of Simulation-Grounded Learning
- Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing
- Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models
- Tikhonov-Fenichel Reductions and their Application to a Novel Modelling Approach for Mutualism
- A Machine Learning Framework for Pathway-Driven Therapeutic Target Discovery in Metabolic Disorders
- From Parameters to Performance: A Data-Driven Study on LLM Structure and Development
- Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework
- BioBO: Biology-informed Bayesian Optimization for Perturbation Design
- Interpreting ResNet-based CLIP via Neuron-Attention Decomposition
- Integrating Mechanistic Modeling and Machine Learning to Study CD4+/CD8+ CAR-T Cell Dynamics with Tumor Antigen Regulation
- Fine-Tuning is Subgraph Search: A New Lens on Learning Dynamics
- Binary Autoencoder for Mechanistic Interpretability of Large Language Models
- CLUE: Conflict-guided Localization for LLM Unlearning Framework
- Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates
- GALAX: Graph-Augmented Language Model for Explainable Reinforcement-Guided Subgraph Reasoning in Precision Medicine
- Towards Atoms of Large Language Models
- RAPTOR-GEN: RApid PosTeriOR GENerator for Bayesian Learning in Biomanufacturing
- Concept-SAE: Active Causal Probing of Visual Model Behavior
- Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation
- Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
- Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare
- Hedonic Neurons: A Mechanistic Mapping of Latent Coalitions in Transformer MLPs
- LLM Interpretability with Identifiable Temporal-Instantaneous Representation
- Mechanistic Fine-tuning for In-context Learning
- Bayesian Inference for Sexual Contact Networks Using Longitudinal Survey Data
- Toward a Theory of Generalizability in LLM Mechanistic Interpretability Research
- Thrust based on changes in angular momentum
- Latent Concept Disentanglement in Transformer-based Language Models
- ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
- Minimalist Explanation Generation and Circuit Discovery
- Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions
- Circuit-Aware Reward Training: A Mechanistic Framework for Longtail Robustness in RLHF
- Excitonic Energy Transfer in Red Algal Photosystem I Reveals an Evolutionary Bridge between Cyanobacteria and Plants
- Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis
- From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning
- Measuring Sparse Autoencoder Feature Sensitivity
- Cyclic Ablation: Testing Concept Localization against Functional Regeneration in AI
- Mechanistic Interpretability as Statistical Estimation: A Variance Analysis of EAP-IG
- Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models
- Feature Identification via the Empirical NTK
- Commutative algebra neural network reveals genetic origins of diseases
- Interpret, prune and distill Donut : towards lightweight VLMs for VQA on document
- BioBlobs: Differentiable Graph Partitioning for Protein Representation Learning
- When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models
- Integrative modelling of biomolecular dynamics
- Interpreting Language Models Through Concept Descriptions: A Survey
- Neural Theorem Proving: Generating and Structuring Proofs for Formal Verification
- Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks
- Understanding Addition and Subtraction in Transformers
- Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders
- Learning Explicit Single-Cell Dynamics Using ODE Representations
- Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models
- Towards CONUS-Wide ML-Augmented Conceptually-Interpretable Modeling of Catchment-Scale Precipitation-Storage-Runoff Dynamics
- Deep learning for flash drought forecasting and interpretation
- Mechanistic Interpretability of Socio-Political Frames in Language Models
- Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test
- The Argument is the Explanation: Structured Argumentation for Trust in Agents
- Disentangling Recall and Reasoning in Transformer Models through Layer-wise Attention and Activation Analysis
- Decomposing Attention To Find Context-Sensitive Neurons
- SoC-DT: Standard-of-Care Aligned Digital Twins for Patient-Specific Tumor Dynamics
- Discovering Transformer Circuits via a Hybrid Attribution and Pruning Framework
- Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models
- Mechanistic-statistical inference of mosquito dynamics from mark-release-recapture data
- Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
- The Logical Implication Steering Method for Conditional Interventions on Transformer Generation
- Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning
- Causal Abstractions, Categorically Unified
- Visual Representations inside the Language Model
- BlackboxNLP-2025 MIB Shared Task: Exploring Ensemble Strategies for Circuit Localization Methods
- Tug-of-war between idioms' figurative and literal interpretations in LLMs
- ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall
- Advancing AI Research Assistants with Expert-Involved Learning
- Biology-driven assessment of deep learning super-resolution imaging of the porosity network in dentin
- Iterated Agent for Symbolic Regression
- RADAR: Mechanistic Pathways for Detecting Data Contamination in LLM Evaluation
- InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
- Egocentric Visual Navigation through Hippocampal Sequences
- Causality \neq\neq Decodability, and Vice Versa: Lessons from Interpreting Counting ViTs
- Impact of Oxygen on DNA Damage Distribution in 3D Genome and Its Correlation to Oxygen Enhancement Ratio under High LET Irradiation
- Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability
- QLENS: Towards A Quantum Perspective of Language Transformers
- A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models
- Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
- Data-Driven Topology Optimization for Multiscale Biomimetic Spinodal Design
- Physical models of embryonic epithelial healing: A review
- Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
- Multi-Scale Probabilistic Generation Theory: A Unified Information-Theoretic Framework for Hierarchical Structure in Large Language Models
- Constrained belief updates explain geometric structures in transformer representations
- CAST: Compositional Analysis via Spectral Tracking for Understanding Transformer Layer Functions
- Functional and parametric identifiability for universal differential equations applied to chemical reaction networks
- Unlocking Out-of-Distribution Generalization in Transformers via Recursive Latent Space Reasoning
- Circuit Insights: Towards Interpretability Beyond Activations
- Causal Time Series Modeling of Supraglacial Lake Evolution in Greenland under Distribution Shift
- Game-Theoretic Discovery of Quantum Error-Correcting Codes Through Nash Equilibria
- Intrinsic Self-Correction in LLMs: Towards Explainable Prompting via Mechanistic Interpretability
- DePass: Unified Feature Attributing by Simple Decomposed Forward Pass
- Extracting Rule-based Descriptions of Attention Features in Transformers
- How role-play shapes relevance judgment in zero-shot LLM rankers
- Layer Specialization Underlying Compositional Reasoning in Transformers
- Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations
- Fighter: Unveiling the Graph Convolutional Nature of Transformers in Time Series Modeling
- Atomic Literary Styling: Mechanistic Manipulation of Prose Generation in Neural Language Models
- Base Models Know How to Reason, Thinking Models Learn When
- I Spy With My Model's Eye: Visual Search as a Behavioural Test for MLLMs
- A Class of Markovian Self-Reinforcing Processes with Power-Law Distributions
- Prospects for Using Artificial Intelligence to Understand Intrinsic Kinetics of Heterogeneous Catalytic Reactions
- Foundation Models for Discovery and Exploration in Chemical Space
- Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
- MolBridge: Atom-Level Joint Graph Refinement for Robust Drug-Drug Interaction Event Prediction
- Stream: Scaling up Mechanistic Interpretability to Long Context in LLMs via Sparse Attention
- Some Attention is All You Need for Retrieval
- Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers
- ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
- Mapping Faithful Reasoning in Language Models
- Transformer brain encoders explain human high-level visual responses
- Mechanistic Interpretability for Neural TSP Solvers
- Mechanism-Guided Residual Lifting and Control Consistent Modeling for Pneumatic Drying Processes
- Overshoot-resolved transition modeling based on field inversion and symbolic regression
- Learning Interpretable Features in Audio Latent Spaces via Sparse Autoencoders
- PAHQ: Accelerating Automated Circuit Discovery through Mixed-Precision Inference Optimization
- Interpreting and Mitigating Unwanted Uncertainty in LLMs
- Sparsity and Superposition in Mixture of Experts
- Mechanistic Interpretability of RNNs emulating Hidden Markov Models
- FaCT: Faithful Concept Traces for Explaining Neural Network Decisions
- Emergence of Minimal Circuits for Indirect Object Identification in Attention-Only Transformers
- Large Language Models Report Subjective Experience Under Self-Referential Processing
- RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching
- Chain-of-Thought Hijacking
- In Defence of Post-hoc Explainability
- MedSAE: Dissecting MedCLIP Representations with Sparse Autoencoders
- BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection
- StreetMath: Study of LLMs' Approximation Behaviors
- Modelling ion channels with a view towards identifiability
- Atlas-Alignment: Making Interpretability Transferable Across Language Models
- Pregnancy as a dynamical paradox: robustness, control and birth onset
- Space as Time Through Neuron Position Learning
- TRISKELION-1: Unified Descriptive-Predictive-Generative AI
- Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI
- Automatically Finding Rule-Based Neurons in OthelloGPT
- Causal Graph Neural Networks for Healthcare
- Interpreting Emergent Features in Deep Learning-based Side-channel Analysis
- LLM Probing with Contrastive Eigenproblems: Improving Understanding and Applicability of CCS
- Addressing divergent representations from causal interventions on neural networks
- APP: Accelerated Path Patching with Task-Specific Pruning
- SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models
- Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning
- Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation
- The Trilemma of Truth in Large Language Models
- SCALAR: Benchmarking SAE Interaction Sparsity in Toy LLMs
- Automated Circuit Interpretation via Probe Prompting
- Rank-1 LoRAs Encode Interpretable Reasoning Signals
- Learning Biomolecular Motion: The Physics-Informed Machine Learning Paradigm
- Visual Exploration of Feature Relationships in Sparse Autoencoders with Curated Concepts
- Fractional neural attention for efficient multiscale sequence processing
- Group Equivariance Meets Mechanistic Interpretability: Equivariant Sparse Autoencoders
- Decomposition of Small Transformer Models
- Weight-sparse transformers have interpretable circuits
- An Automated Framework for Analyzing Structural Evolution in On-the-fly Non-adiabatic Molecular Dynamics Using Autoencoder and Multiple Molecular Descriptors
- Bridging the genotype-phenotype gap with generative artificial intelligence
- From Black-Box to White-Box: Control-Theoretic Neural Network Interpretability
- Explainable deep learning framework for cancer therapeutic target prioritization leveraging PPI centrality and node embeddings
- Comment on "Repair of DNA Double-Strand Breaks Leaves Heritable Impairment to Genome Function"
- Which Sparse Autoencoder Features Are Real? Model-X Knockoffs for False Discovery Rate Control
- Differentiable Electrochemistry: A paradigm for uncovering hidden physical phenomena in electrochemical systems
- nnterp: A Standardized Interface for Mechanistic Interpretability of Transformers
- Judicial Sentencing Prediction Based on Hybrid Models and Two-Stage Learning Algorithms
- Chromatographic Peak Shape from Stochastic Model: Analytic Time-Domain Expression in Terms of Physical Parameters and Conditions under which Heterogeneity Reduces Tailing
- Beyond Protein Language Models: An Agentic LLM Framework for Mechanistic Enzyme Design
- Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks
- Interpreting GFlowNets for Drug Discovery: Extracting Actionable Insights for Medicinal Chemistry
- Pathway to Relevance: How Cross-Encoders Implement a Semantic Variant of BM25
- Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models
- Vector Arithmetic in Concept and Token Subspaces
- The Horcrux: Mechanistically Interpretable Task Decomposition for Detecting and Mitigating Reward Hacking in Embodied AI Systems
- Understanding Counting Mechanisms in Large Language and Vision-Language Models
- BlockCert: Certified Blockwise Extraction of Transformer Mechanisms
- Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits
- Approximate Bayesian Computation Made Easy: A Practical Guide to ABC-SMC for Dynamical Systems with \texttt{pymc}
- Mechanistic Interpretability for Transformer-based Time Series Classification
- Physics Steering: Causal Control of Cross-Domain Concepts in a Physics Foundation Model
- Interpretability for Time Series Transformers using A Concept Bottleneck Framework
- Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations
- A race to belief: How Evidence Accumulation shapes trust in AI and Human informants
- FoldSAE: Learning to Steer Protein Folding Through Sparse Representations
- Unsupervised decoding of encoded reasoning using language model interpretability
- TrendGNN: Towards Understanding of Epidemics, Beliefs, and Behaviors
- VCWorld: A Biological World Model for Virtual Cell Simulation
- EXP-CAM: Explanation Generation and Circuit Discovery Using Classifier Activation Matching
- HyperADRs: A Hierarchical Hypergraph Framework for Drug-Gene-ADR Prediction
- ProteinPNet: Prototypical Part Networks for Concept Learning in Spatial Proteomics
- Translating Measures onto Mechanisms: The Cognitive Relevance of Higher-Order Information
- Mechanisms of Symbol Processing for In-Context Learning in Transformer Networks
- Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability
- Approximate Bayesian Inference on Mechanisms of Network Growth and Evolution
- AtomDisc: An Atom-level Tokenizer that Boosts Molecular LLMs and Reveals Structure--Property Associations
- Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN
- Neural Policy Composition from Free Energy Minimization
- Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective
- Minuet: A Diffusion Autoencoder for Compact Semantic Compression of Multi-Band Galaxy Images
- Sparse Attention Post-Training for Mechanistic Interpretability
- Mechanistic Interpretability of Antibody Language Models Using SAEs
- Rethinking Sparse Autoencoders: Select-and-Project for Fairness and Control from Encoder Features Alone
- On the Theoretical Foundation of Sparse Dictionary Learning in Mechanistic Interpretability
- A network-driven framework for enhancing gene-disease association studies in coronary artery disease
- XMCQDPT2-Fidelity Transfer-Learning Potentials and a Wavepacket Oscillation Model with Power-Law Decay for Ultrafast Photodynamics
- ExPUFFIN: Thermodynamic Consistent Viscosity Prediction in an Extended Path-Unifying Feed-Forward Interfaced Network
- Mechanistic Interpretability of GPT-2: Lexical and Contextual Layers in Sentiment Analysis
- Same Content, Different Answers: Cross-Modal Inconsistency in MLLMs
- A microstructural rheological model for transient creep in polycrystalline ice
- Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
- Bayesian Co-Navigation of a Computational Physical Model and AFM Experiment to Autonomously Survey a Combinatorial Materials Library
- Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignment
- SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation
- Interpretable and Steerable Concept Bottleneck Sparse Autoencoders
- Unlocking the Address Book: Dissecting the Sparse Semantic Structure of LLM Key-Value Caches via Sparse Autoencoders
- SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation
- Physics-informed neural network for fatigue life prediction of irradiated austenitic and ferritic/martensitic steels
- ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts
- Learning continuous SOC-dependent thermal decomposition kinetics for Li-ion cathodes using KA-CRNNs
- Who is In Charge? Dissecting Role Conflicts in Instruction Following
- SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks
- AI Epidemiology: achieving explainable AI through expert oversight patterns
- Machine Learning Framework for Thrombosis Risk Prediction in Rotary Blood Pumps
- RP-CATE: Recurrent Perceptron-based Channel Attention Transformer Encoder for Industrial Hybrid Modeling
- R-GenIMA: Integrating Neuroimaging and Genetics with Interpretable Multimodal AI for Alzheimer's Disease Progression
- Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability
- Block-Recurrent Dynamics in Vision Transformers
- Sign-Aware Multistate Jaccard Kernels and Geometry for Real and Complex-Valued Signals
- The Deepfake Detective: Interpreting Neural Forensics Through Sparse Features and Manifolds
- Omni-Weather: Unified Multimodal Foundation Model for Weather Generation and Understanding
- Information is localized in growing network models
- Mono- and Polyauxic Growth Kinetics: A Semi-Mechanistic Framework for Complex Biological Dynamics
- Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation
- Mechanistic Analysis of Circuit Preservation in Federated Learning
- A Paradigm Shift in Human Neuroscience Research: Progress, Prospects, and a Proof of Concept for Population Neuroscience
- EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs
- Triangulation as an Acceptance Rule for Multilingual Mechanistic Interpretability
- BIOME-Bench: A Benchmark for Biomolecular Interaction Inference and Multi-Omics Pathway Mechanism Elucidation from Scientific Literature
- Connecting strain rate dependence of fcc metals to dislocation avalanche signatures
- Towards mechanistic understanding in a data-driven weather model: internal activations reveal interpretable physical features
- "X-ray Coulomb Counting" to understand electrochemical systems
- Bridging Visual Intuition and Chemical Expertise: An Autonomous Analysis Framework for Nonadiabatic Dynamics Simulations via Mentor-Engineer-Student Collaboration
- Adversarial Lens: Exploiting Attention Layers to Generate Adversarial Examples for Evaluation
- Emergent World Beliefs: Exploring Transformers in Stochastic Games
- How much neuroscience does a neuroscientist need to know?
- Trustworthy Data-Driven Wildfire Risk Prediction and Understanding in Western Canada
- Central Dogma Transformer: Towards Mechanism-Oriented AI for Cellular Understanding
- Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models
- When the Coffee Feature Activates on Coffins: An Analysis of Feature Extraction and Steering for Mechanistic Interpretability
- Mechanistic Interpretability of Large-Scale Counting in LLMs through a System-2 Strategy
- Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencoders
- Bridging Mechanistic Interpretability and Prompt Engineering with Gradient Ascent for Interpretable Persona Control
- A Pre-trained Reaction Embedding Descriptor Capturing Bond Transformation Patterns
- Local Multimodal Dynamics in Mixed Ionic-Electronic Conductors and Their Fingerprints in Organic Electrochemical Transistor Operation
- When Models Manipulate Manifolds: The Geometry of a Counting Task
- Interpreting Transformers Through Attention Head Intervention
- Analytical review of nanoplastic bioaccumulation data and a unified toxicokinetic model: from teleosts to human brain
- Molecular signatures of pressure-induced phase transitions in a lipid bilayer
- A Backpropagation-Free Feedback-Hebbian Network for Continual Learning Dynamics
- AlignSAE: Concept-Aligned Sparse Autoencoders
- Physics-constrained Gaussian Processes for Predicting Shockwave Hugoniot Curves
- Time Travel Engine: A Shared Latent Chronological Manifold Enables Historical Navigation in Large Language Models
- Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers
- LLM-Powered Social Digital Twins: A Framework for Simulating Population Behavioral Response to Policy Interventions
- Vocabulary Expansion of Large Language Models via Kullback-Leibler-Based Self-Distillation
- Toward Understanding Unlearning Difficulty: A Mechanistic Perspective and Circuit-Guided Difficulty Metric
- Where Knowledge Collides: A Mechanistic Study of Intra-Memory Knowledge Conflict in Language Models
- Diagnosing Generalization Failures in Fine-Tuned LLMs: A Cross-Architectural Study on Phishing Detection
- Dedifferentiation stabilizes stem cell lineages: From CTMC to diffusion theory and thresholds
- An Epidemiological Modeling Take on Religion Dynamics
- From Adversarial Poetry to Adversarial Tales: An Interpretability Research Agenda
- Metabolomic Biomarker Discovery for ADHD Diagnosis Using Interpretable Machine Learning
- Mechanistic Learning for Survival Prediction in NSCLC Using Routine Blood Biomarkers and Tumor Kinetics
- From Interpretability to Performance: Optimizing Retrieval Heads for Long-Context Language Models
- Reasoning Models Generate Societies of Thought
- BACH-V: Bridging Abstract and Concrete Human-Values in Large Language Models
- Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
- Patterning: The Dual of Interpretability
- Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition
- The Physics of the Dancing \emph{Deity}: Coupled Oscillators in Himalayan Processions
- Race, Ethnicity and Their Implication on Bias in Large Language Models
- A Machine Learning--Based Surrogate EKMA Framework for Diagnosing Urban Ozone Formation Regimes: Evidence from Los Angeles
- Long-term prediction of ENSO with physics-guided Deep Echo State Networks
- Persistent Sheaf Laplacian Analysis of Protein Stability and Solubility Changes upon Mutation
- Single-Node Wilson--Cowan Model Accounts for Speech-Evoked γγ-Band Deficits in Schizophrenia
- LLM Powered Social Digital Twins: A Framework for Simulating Population Behavioral Response to Policy Interventions
- DiSPA: Differential Substructure-Pathway Attention for Drug Response Prediction
- White-Box mHC: Electromagnetic Spectrum-Aware and Interpretable Stream Interactions for Hyperspectral Image Classification
- Emergence and Evolution of Interpretable Concepts in Diffusion Models
- Latent Causal Diffusions for Single-Cell Perturbation Modeling
- A Monosemantic Attribution Framework for Stable Interpretability in Clinical Neuroscience Large Language Models
- Interpretability of the Intent Detection Problem: A New Approach
- Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers
- How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability
- Data-driven sparse identification of vector-borne disease dynamics with memory effects
- Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs
- Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures
- Putting a Face to Forgetting: Continual Learning meets Mechanistic Interpretability
- Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
- Amortized Spectral Kernel Discovery via Prior-Data Fitted Network
- A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima
- A Multi-agent Framework for Physical Laws Discovery
- Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models
- Sparse or Dense? A Mechanistic Estimation of Computation Density in Transformer-based LLMs
- Beyond Conditional Computation: Retrieval-Augmented Genomic Foundation Models with Gengram
- BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Elicitation
- Universal Redundancies in Time Series Foundation Models
- Mechanistic Interpretability of Brain-to-Speech Models Across Speech Modes
- Toward Interpretable and Generalizable AI in Regulatory Genomics
- Supervised sparse auto-encoders as unconstrained feature models for semantic composition
- Agentic Framework for Epidemiological Modeling
- Explaining the Explainer: Understanding the Inner Workings of Transformer-based Symbolic Regression Models
- Mechanistic Interpretability as Statistical Estimation: A Variance Analysis
- MARADONER: Motif Activity Response Analysis Done Right
- BioGen: An Evidence-Grounded Framework for Interpreting RNA-seq Gene Clusters in Antimicrobial Resistance Research
- Disentangling meaning from language in LLM-based machine translation
- Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish
- PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling
- DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
- From Vision to Decision: Neuromorphic Control for Autonomous Navigation and Tracking
- Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities
- A waveguide kinetics framework for electrochemical polarization
- Somatic Mechanotherapy Activates a Spatiotemporally Synchronized CPTC Wnt Axis for Gut Regeneration
- Causal Front-Door Adjustment for Robust Jailbreak Attacks on LLMs
- Advancing Opinion Dynamics Modeling with Neural Diffusion-Convection-Reaction Equation
- Path Sampling for Rare Events Boosted by Machine Learning
- Explanations are a Means to an End: Decision Theoretic Explanation Evaluation
- Momentum Attention: The Physics of In-Context Learning and Spectral Forensics for Mechanistic Interpretability
- The Quantum Sieve Tracer: A Hybrid Framework for Layer-Wise Activation Tracing in Large Language Models
- Habitat heterogeneity and dispersal network structure as drivers of metacommunity dynamics
- How (Not) to Hybridize Neural and Mechanistic Models for Epidemiological Forecasting
- Reasoning aligns language models to human cognition
- How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location
- Patches of Nonlinearity: Instruction Vectors in Large Language Models
- Revisiting Transformers with Insights from Image Filtering and Boosting
- Towards Understanding Multimodal Fine-Tuning: Spatial Features
- CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs
- Learning Alzheimer's Disease Signatures by bridging EEG with Spiking Neural Networks and Biophysical Simulations
- CPTCs Drive Somatic-Visceral Communication via the Wnt Axis in Somatic Mechanotherapy: A Single-Cell Deep Learning Study
- Tiny Moves: Game-based Hypothesis Refinement
- From Circuits to Dynamics: Understanding and Stabilizing Failure in 3D Diffusion Transformers
- Can Large Language Models Make Everyone Happy?
- Med-SegLens: Latent-Level Model Diffing for Interpretable Medical Image Segmentation
- Control Reinforcement Learning: Token-Level Mechanistic Analysis via Learned SAE Feature Steering
- EVA: Towards a universal model of the immune system
- DEpiABS: Differentiable Epidemic Agent-Based Simulator
- Protein Circuit Tracing via Cross-layer Transcoders
- Dopamine: Brain Modes, Not Brains
- Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features
- Revealing Exotic Nanophase Iron in Lunar Samples Through Impact-Driven Spatial Fingerprints
- Learning Glioblastoma Tumor Heterogeneity Using Brain Inspired Topological Neural Networks
- Layer-Specific Fine-Tuning for Improved Negation Handling in Medical Vision-Language Models
- Inner Loop Inference for Pretrained Transformers: Unlocking Latent Capabilities Without Training
- Predicting Company Growth using Scaling Theory informed Machine Learning
- Singular Vectors of Attention Heads Align with Features
- Finding Highly Interpretable Prompt-Specific Circuits in Language Models
- What Do Neurons Listen To? A Neuron-level Dissection of a General-purpose Audio Model
- Seeing to Generalize: How Visual Data Corrects Binding Shortcuts
- Universal Framework for Decomposing Ionic Transport into Interpretable Mechanisms
- Systematic Evaluation of Single-Cell Foundation Model Interpretability Reveals Attention Captures Co-Expression Rather Than Unique Regulatory Signal
- Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy
- Exploring Memory Effects: Sparse Identification in Vector-Borne Diseases
- Discovering Universal Activation Directions for PII Leakage in Language Models
- On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking
- Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees
- Quantifying LLM Attention-Head Stability: Implications for Circuit Universality
- A Probabilistic Framework for LLM-Based Model Discovery
- Simplifying Outcomes of Language Model Component Analyses with ELIA
- Mechanistic Interpretability with Sparse Autoencoder Neural Operators
- Hiding in Plain Text: Detecting Concealed Jailbreaks via Activation Disentanglement
- Beyond Behavioural Trade-Offs: Mechanistic Tracing of Pain-Pleasure Decisions in an LLM
- Temperature as a Dynamically Maintained Steady State: Photonic Mechanisms, Maintenance Cost, and the Limits of the Infinite-Reservoir Idealization
- Unveiling Scaling Laws of Parameter Identifiability and Uncertainty Quantification in Data-Driven Biological Modeling
- Robust Model Selection for Discovery of Latent Mechanistic Processes
- ABM-UDE: Developing Surrogates for Epidemic Agent-Based Models via Scientific Machine Learning
- MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning
- SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented Evaluation
- MetaOthello: A Controlled Study of Multiple World Models in Transformers
- Certified Circuits: Stability Guarantees for Mechanistic Circuits
- Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks
- Transformers converge to invariant algorithmic cores
- AR&D: A Framework for Retrieving and Describing Concepts for Interpreting AudioLLMs
- On De-Individuated Neurons: Continuous Symmetries Enable Dynamic Topologies
- Diagnosing Generalization Failures from Representational Geometry Markers
- Emerging Human-like Strategies for Semantic Memory Foraging in Large Language Models
- Decoding Answers Before Chain-of-Thought: Evidence from Pre-CoT Probes and Activation Steering
- Interpretable Cross-Network Attention for Resting-State fMRI Representation Learning
- Emergence of Spatial Representation in an Actor-Critic Agent with Hippocampus-Inspired Sequence Generator
- A Closed-loop Framework to Discriminate Models Using Optimal Control
- What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models
- Inferring brain plasticity rule under long-term stimulation with structured recurrent dynamics
- TumorFlow: Physics-Guided Longitudinal MRI Synthesis of Glioblastoma Growth
- Tracing Pharmacological Knowledge In Large Language Models
- Observing and Controlling Features in Vision-Language-Action Models
- The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology
- BioLLMAgent: A Hybrid Framework with Enhanced Structural Interpretability for Simulating Human Decision-Making in Computational Psychiatry
- Stochastic Optimal Feedforward-Feedback Control for Partially Observable Sensorimotor Systems
- Steering Awareness: Models Can Be Trained to Detect Activation Steering
- Lost in Translation: Simulation-Informed Bayesian Inference Improves Understanding of Molecular Motion From Neutron Scattering
- The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR\rightarrow\rightarrowLLM Pipelines?
- Learning Concept Bottleneck Models from Mechanistic Explanations
- Are Audio-Language Models Listening? Audio-Specialist Heads for Adaptive Audio Steering
- Causal Interpretation of Neural Network Computations with Contribution Decomposition
- Computational Multi-Agents Society Experiments: Social Modeling Framework Based on Generative Agents
- Physical Models of Embryonic Epithelial Healing
- Fast reconstruction of degenerate populations of conductance-based neuron models from spike times
- The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs
- Distilled Circuits: A Mechanistic Study of Internal Restructuring in Knowledge Distillation
- Protein Counterfactuals via Diffusion-Guided Latent Optimization
- Backdoor Directions in Vision Transformers
- Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness
- Implicit Statistical Inference in Transformers: Approximating Likelihood-Ratio Tests In-Context
- Discovery of a Hematopoietic Manifold in scGPT Yields a Method for Extracting Performant Algorithms from Biological Foundation Model Internals
- From Data Statistics to Feature Geometry: How Correlations Shape Superposition
- The Affine Divergence: Aligning Activation Updates Beyond Normalisation
- Dissecting Chronos: Sparse Autoencoders Reveal Causal Feature Hierarchies in Time Series Foundation Models
- Exhaustive Circuit Mapping of a Single-Cell Foundation Model Reveals Massive Redundancy, Heavy-Tailed Hub Architecture, and Layer-Dependent Differentiation Control
- Chem4DLLM: 4D Multimodal LLMs for Chemical Dynamics Understanding
- ELISA: An Interpretable Hybrid Generative AI Agent for Expression-Grounded Discovery in Single-Cell Genomics
- Locating Demographic Bias at the Attention-Head Level in CLIP's Vision Encoder
- Size-Dependent Fluorescence Kinetics Reveal Contributions of Intrinsic Quenching and Singlet-Triplet Annihilation during LHCII Aggregation
- Attention Gathers, MLPs Compose: A Causal Analysis of an Action-Outcome Circuit in VideoViT
- Hydrogen-atom roaming reactions in water clusters: Unveiling an unusual dimension of water reactivity through first-principles calculations and machine learning
- Deep Learning for Blood-Brain Barrier Permeability Prediction: From Discriminative Models to Mechanism-Aware Design
- Mechanistic Foundations of Goal-Directed Control
- Directional Routing in Transformers
- A minimal model of pump foil dynamics
- LLM-Powered Flood Depth Estimation from Social Media Imagery: A Vision-Language Model Framework with Mechanistic Interpretability for Transportation Resilience
- Intracellular Measurement-Informed Multiscale Modeling for Scalable iPSC Manufacturing
- Improving Epidemic Analyses with Privacy-Preserving Integration of Sensitive Data
- Bridging Crystal Structure and Material Properties via Bond-Centric Descriptors
- Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
- From Snapshots to Symphonies: The Evolution of Protein Prediction from Static Structures to Generative Dynamics and Multimodal Interactions
- Interpretability without actionability: mechanistic methods cannot correct language model errors despite near-perfect internal representations
- Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients
- Do Language Models Encode Semantic Relations? Probing and Sparse Feature Analysis
- Fundamental Limits of Neural Network Sparsification: Evidence from Catastrophic Interpretability Collapse
- Causal Intervention Framework for Variational Auto Encoder Mechanistic Interpretability
- Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models
- Interpreting Reinforcement Learning Model Behavior via Koopman with Control
- A Unified Phase-native Computational Principle Governs Hippocampal Spike Timing and Neural Coding
- Accurate Open-Loop Control of a Soft Continuum Robot Through Visually Learned Latent Representations
- GeoLAN: Geometric Learning of Latent Explanatory Directions in Large Language Models
- CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs
- Interpreting the Synchronization Gap: The Hidden Mechanism Inside Diffusion Transformers
- Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning
- Graph-based data-driven discovery of interpretable laws governing corona-induced noise and radio interference for high-voltage transmission lines
- GIP-RAG: An Evidence-Grounded Retrieval-Augmented Framework for Interpretable Gene Interaction and Pathway Impact Analysis
- TRACE: A Multi-Agent System for Autonomous Physical Reasoning in Seismological
- INTRYGUE: Induction-Aware Entropy Gating for Reliable RAG Uncertainty Estimation
- MCLR: Improving Conditional Modeling in Visual Generative Models via Inter-Class Likelihood-Ratio Maximization and Establishing the Equivalence between Classifier-Free Guidance and Alignment Objectives
- Does Mechanistic Interpretability Transfer Across Data Modalities? A Cross-Domain Causal Circuit Analysis of Variational Autoencoders
- Fair splits flip the leaderboard: CHANRG reveals limited generalization in RNA secondary-structure prediction
- Whether, Not Which: Mechanistic Interpretability Reveals Dissociable Affect Reception and Emotion Categorization in LLMs
- Symbolic--KAN: Kolmogorov-Arnold Networks with Discrete Symbolic Structure for Interpretable Learning
- Steering LLMs for Culturally Localized Generation
- SafeSeek: Universal Attribution of Safety Circuits in Language Models
- Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models
- Closing the Confidence-Faithfulness Gap in Large Language Models
- Mechanistically Interpreting Compression in Vision-Language Models
- TRACE: A Multi-Agent System for Autonomous Physical Reasoning for Seismology
- Identifying Connectivity Distributions from Neural Dynamics Using Flows
- Entanglement as Memory: Mechanistic Interpretability of Quantum Language Models
- Sparse Auto-Encoders and Holism about Large Language Models
- EVA: Bridging Performance and Human Alignment in Hard-Attention Vision Models for Image Classification
- Steering Sparse Autoencoder Latents to Control Dynamic Head Pruning in Vision Transformers (Student Abstract)
- Tracking Equivalent Mechanistic Interpretations Across Neural Networks
- BIOGEN: Evidence-Grounded Multi-Agent Reasoning Framework for Transcriptomic Interpretation in Antimicrobial Resistance
- Detecting low left ventricular ejection fraction from ECG using an interpretable and scalable predictor-driven framework
- Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation
- Low-Rank Adaptation Reduces Catastrophic Forgetting in Sequential Transformer Encoder Fine-Tuning: Controlled Empirical Evidence and Frozen-Backbone Representation Probes
- Analytical characterisation of the Mi- and To-phases in HeMiTo dynamics: exponential growth and logistic saturation of toxic prion-like proteins
- From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks
- Thinking Wrong in Silence: Backdoor Attacks on Continuous Latent Reasoning
- Spatiotemporal Characterization of Overdose Mortality in Georgia, USA Using Spectral and Nonlinear Interaction Analysis, 2003-2021
- Identifying and Estimating Causal Direct Effects Under Unmeasured Confounding
- Finding Belief Geometries with Sparse Autoencoders
- Revealing the Learning Dynamics of Long-Context Continual Pre-training
- Do Audio-Visual Large Language Models Really See and Hear?
- A Multi-Level Causal Intervention Framework for Mechanistic Interpretability in Variational Autoencoders
- Automated Attention Pattern Discovery at Scale in Large Language Models
- Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs
- Feature-Aware Anisotropic Local Differential Privacy for Utility-Preserving Graph Representation Learning in Metal Additive Manufacturing
- Learning continuous state of charge dependent thermal decomposition kinetics for Li-ion cathodes using Kolmogorov-Arnold Chemical Reaction Neural Networks (KA-CRNNs)
- ConceptTracer: Interactive Analysis of Concept Saliency and Selectivity in Neural Representations
- The Mechanistic Invariance Test: Genomic Language Models Fail to Learn Positional Regulatory Logic
- Improving Robustness In Sparse Autoencoders via Masked Regularization
- LAG-XAI: A Lie-Inspired Affine Geometric Framework for Interpretable Paraphrasing in Transformer Latent Spaces
- Disentangling MLP Neuron Weights in Vocabulary Space
- Spectral Edge Dynamics Reveal Functional Modes of Learning
- SALLIE: Safeguarding Against Latent Language & Image Exploits
- MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives
- Towards Rapid Constitutive Model Discovery from Multi-Modal Data: Physics Augmented Finite Element Model Updating (paFEMU)
- Transferable FB-GNN-MBE Framework for Potential Energy Surfaces: Data-Adaptive Transfer Learning in Deep Learned Many-Body Expansion Theory
- Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics
- Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?
- Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
- CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models
- The Myth of Expert Specialization in MoEs: Why Routing Reflects Geometry, Not Necessarily Domain Expertise
- Interpretable Relational Inference with LLM-Guided Symbolic Dynamics Modeling
- Causal Drawbridges: Characterizing Gradient Blocking of Syntactic Islands in Transformer LMs
- Weight Patching: Toward Source-Level Mechanistic Localization in LLMs
- CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations
- Mechanistic Decoding of Cognitive Constructs in LLMs
- Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers
- LLM Reasoning Is Latent, Not the Chain of Thought
- The Topological Dual of a Dataset: A Logic-to-Topology Encoding for AlphaGeometry-Style Data
- Where is the Mind? Persona Vectors and LLM Individuation
- Applications of deep generative models to DNA reaction kinetics and to cryogenic electron microscopy
- Surgical Repair of Insecure Code Generation in LLMs
- DLCM: a versatile multi-level solver for heterogeneous multicellular systems
- Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models
- MDAgent: A Multi-Agent Framework for End-to-End Molecular Dynamics Research
- Mechanistic Interpretability Tool for AI Weather Models
- Mechanistic Decoding of Cognitive Constructs in Large Language Models
- Large Language Models Meet Biomedical Knowledge Graphs for Mechanistically Grounded Therapeutic Prioritization
- Directional Confusions Reveal Divergent Inductive Biases Through Rate-Distortion Geometry in Human and Machine Vision
- Locating acts of mechanistic reasoning in student team conversations with mechanistic machine learning
- There Will Be a Scientific Theory of Deep Learning
- Beyond Land Surface Temperature: Explainable Spatial Machine Learning Reveals Urban Morphology Effects on Human-Centric Heat Stress
- Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
- A systematic evaluation of vision-language models for observational astronomical reasoning tasks
- Amplified Urban Climate Extremes from Global Warming-Urbanization Synergy: Toward a Physics-Informed Intelligence Paradigm
- Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer
- Test of Time: Rethinking Temporal Signal of Benchmark Contamination
- AIPsy-Affect: A Keyword-Free Clinical Stimulus Battery for Mechanistic Interpretability of Emotion in Language Models
- VAMP-Net: An Interpretable Multi-Path Network of Genomic Permutation-Invariant Set Attention and Quality-Aware 1D-CNN for MTB Drug Resistance
- DeepImagine: Learning Biomedical Reasoning via Successive Counterfactual Imagining
- From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models
- Learning biophysical models of gene regulation with probability flow matching
- Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models
- Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate
- Rare but Resilient: Dispersal diversity buffers species vulnerability
- reward-lens: A Mechanistic Interpretability Library for Reward Models
- Amplified Urban Climate Extremes from Global Warming-Urbanization Synergy: A Physics-Informed Intelligence Paradigm
- From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models
- Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models
- Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction
- Automated Interpretability and Feature Discovery in Language Models with Agents
- Constructing Interpretable Features from Compositional Neuron Groups
- Barren Plateaus as Destructive Interference: A Diagnostic Framework and Implications for Structured Ansatzes
- Sampled-data Robust Control of Electrically Stimulated Engineered Cell Factories
- Modelling the electrophysiological interactions between human pluripotent cell-derived cardiomyocite grafts and host ventricular tissue
- Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability
- Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation
- How Language Models Process Negation
- Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs
- Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
- A process-based dynamic occupancy model to study range dynamics under non-equilibrium conditions
- Crafting Reversible SFT Behaviors in Large Language Models
- SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders
- From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features
- Patch-Effect Graph Kernels for LLM Interpretability
- SMolLM: Small Language Models Learn Small Molecular Grammar
- Higher-order interactions in ecology can be hidden in plain sight
- Playing the network backward: A Game Theoretic Attribution Framework
- Time series saliency maps: explaining models across multiple domains
- Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training
- Resolving the bias-precision paradox with stochastic causal representation learning for personalized medicine
- Temporal Functional Circuits: From Spline Plots to Faithful Explanations in KAN Forecasting
- Negative Before Positive: Asymmetric Valence Processing in Large Language Models
- Position: Mechanistic Interpretability Must Disclose Identification Assumptions for Causal Claims
- Jagged AI in Scientific Peer Review: Evidence from POMP Data Analysis
- Distributional simplicity bias and effective convexity in Energy Based Models
- PPI-Net connects molecular protein interactions to functional processes in disease
- Supervised sparse auto-encoders for interpretable and compositional representations
- Mean-Pooled Cosine Similarity is Not Length-Invariant: Theory and Cross-Domain Evidence for a Length-Invariant Alternative
- Activation Differences Reveal Backdoors: A Comparison of SAE Architectures
- Generative Modeling with Flux Matching
- Emergent Manifold Separability during Reasoning in Large Language Models
- Essential Role of Extrinsic Noise in Models of E. coli Division Control
- PLOT: Progressive Localization via Optimal Transport in Neural Causal Abstraction
- Beyond the Black Box: Interpretability of Agentic AI Tool Use
- The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts
- Estimating Consensus Epidemic Trajectories via a Constrained Power Fréchet Mean with Functional Registration
- From Syntax to Semantics: Unveiling the Emergence of Chirality in SMILES Translation Models
- Dissecting Jet-Tagger Through Mechanistic Interpretability
- Hidden Error Awareness in Chain-of-Thought Reasoning: The Signal Is Diagnostic, Not Causal
- The Wittgensteinian Representation Hypothesis: Is Language the Attractor of Multimodal Convergence?
- SMIXAE: Towards Unsupervised Manifold Discovery in Language Models
- Data-driven Circuit Discovery for Interpretability of Language Models
- Investigating Anisotropy in Visual Grounding under Controlled Counterfactual Perturbations
- From Mechanistic to Compositional Interpretability
- Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off
- Architecture, Not Scale: Circuit Localization in Large Language Models
- Causal Dimensionality of Transformer Representations: Measurement, Scaling, and Layer Structure
- Hidden Heroes and Gradient Bloats: Layer-Wise Redundancy Inverts Attribution in Transformers
- Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression
- Hiding in Plain Sight: Detectability-Aware Antidistillation of Reasoning Models
- Belief or Circuitry? Causal Evidence for In-Context Graph Learning
- Machine learning the non-radiative decay modes in photochemical processes
- How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits
- LLM Advertisement based on Neuron Auctions
- What Cohort INRs Encode and Where to Freeze Them
- GKnow: Measuring the Entanglement of Gender Bias and Factual Gender
- Mechanistic Interpretability of ASR models using Sparse Autoencoders
- Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
- Native Explainability for Bayesian Confidence Propagation Neural Networks: A Framework for Trusted Brain-Like AI
- bViT: Investigating Single-Block Recurrence in Vision Transformers for Image Recognition
- The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime
- Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
- Dual-Pathway Circuits of Object Hallucination in Vision-Language Models
- All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs
- OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting
- When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability
- Understanding Imbalanced Forgetting in Rehearsal-Based Class-Incremental Learning
- The Rate-Distortion-Polysemanticity Tradeoff in SAEs
- Exploring Geographic Relative Space in Large Language Models through Activation Patching
- Exemplar Partitioning for Mechanistic Interpretability
- Finding Interpretable Prompt-Specific Circuits in Language Models
- Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity
- Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
- XAI and Statistical Analysis for Reliable Intrusion Detection in the UAVIDS-2025 Dataset: From Tree to Hybrid and Tabular DNN Ensembles
- Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models
- Multi-Turn Neural Transparency: Surfacing Neural Activations Improves User Calibration to LLM Behavioral Drift
- Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling
- StructLens: A Structural Lens for Language Models via Maximum Spanning Trees
- Toy Combinatorial Interpretability Models Reveal Lottery Tickets in Early Feature Space
- A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint Principle
- Beyond Linear Superposition: Discovering Climate Features in AI Weather Models with KAN-SAE
- Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies
- HYVINT: Intensity-Driven Hypergraph Generation with Variational Representations
- Sensitivity analysis-guided model reduction of a mathematical model of pembrolizumab therapy for de novo metastatic MSI-H/dMMR colorectal cancer
- Mechanistically Interpretable Neural Encoding Reveals Fine-Grained Functional Selectivity in Human Visual Cortex
- Where Does Authorship Signal Emerge in Encoder-Based Language Models?
- Mechanisms of Object Localization in Vision-Language Models
- Symmetry Matters: Auditing and Symmetrizing 3D Generative Models
- Transformers Linearly Represent Highly Structured World Models
- Lost and Found in Translation: Variational Diagnostics for Neural Codebook Channels
- Post-Hoc Understanding of Metaphor Processing in Decoder-Only Language Models via Conditional Scale Entropy
- From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach
- A Sharper Picture of Generalization in Transformers
- Multi-Modal Machine Learning for Population- and Subject-Specific lncRNA-Type 2 Diabetes Association Analysis
- Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System
- Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs
- Mechanisms of Misgeneralization in Physical Sequence Modeling
- LEAP: A closed-loop framework for perovskite precursor additive discovery
- Reading Task Failure Off the Activations: A Sparse-Feature Audit of GPT-2 Small on Indirect Object Identification
- Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
- Drivers of Transient Dynamics and Persistence in Dengue: Insights from Sensitivity and Stochastic Modeling
- A Mechanistic Explanatory Strategy for XAI
- Protein Thoughts: Interpretable Reasoning with Tree of Thoughts and Embedding-Space Flow Matching for Protein-Protein Interaction Discovery
- Every Component is a Lookup: Token Attribution and Composition from a Single Decomposition
- Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection
- Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography
- Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
- From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Data
- Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy
- Is Inference Mediated by Distinct Semantic Structures in LLMs? A Mechanistic Interpretation
- Continuous-Depth Field Theory for Transformer Patching and Mechanistic Interpretability
- Explainable Retinal Imaging for Prediction of Multi-Organ Dysfunction in Type 2 Diabetes
- The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth
- Investigating the Effect of Network Pruning on Performance and Interpretability
- Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Transformer to Pythia-70m
- Learning dynamical systems with biochemically informed neural ordinary differential equations
- Towards Verifiable Transformers: Solver-Checkable Circuit Explanations
- Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
- Can Broad Biomedical Knowledge be Contextualized into Scenario-Grounded Propositions?
- Emergent Causal-Geometric Dynamics Across Depth in Large Language Models
- SL-BiLEM: Structured Learnable Behavior-in-the-Loop Epidemic Modeling for Forecasting and Policy Evaluation
- CART Random Forests as Sequential Allocation over Random Opportunity Sets: A Stochastic-Control Theory of Ensemble Risk
- MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability
- Stance Detection in Prediction Markets: Addressing Imbalanced Trader Commentary via Counterfactual Augmentation and Market Context
- Determinants of Phase-Separation Propensities, Material States, and Material Properties of Biomolecular Condensates
- Cultural Binding Heads in Language Models
- Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training
- Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs
- Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models
- The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models
- What drives performance in molecular MPNNs? An operator-level factorial benchmark
- Dissecting the Black Box: Circuit-Level Analysis of LLM Vulnerability Detection
- Xetrieval: Mechanistically Explaining Dense Retrieval
- The Curse of Helpfulness: Inverse Scaling Law in Robustness to Distractor Instructions via DistractionIF
- Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge
- Feature Geometry of LoRA Adapters: A Sparse Autoencoder Analysis of Representational Divergence in Fine-Tuned Language Models
- Positional versus Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length Generalization
- Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation
- TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery
- CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware Alignment
- A Bayesian Framework for Uncertainty-Aware Estimation of Main Pulmonary Artery Velocity Profiles from Phase-Contrast MRI
- Ubiquity of Emergent Hebbian Dynamics in Regularized Learning
- Discovering a Zeta Map Algorithm on Dyck Paths via Mechanistic Interpretability
- Translation Heads: Disentangling meaning from language in LLM-based machine translation
- Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States
- A Monosemantic Attribution Framework for Stable Interpretability in Clinical Neuroscience Transformer-Based Language Models
- When Do Attention Circuits Form? Developmental Trajectories of Capability and Attention-Sink Emergence Across Three 1B-ClassArchitectures
- Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation
- Matter to Mechanism: A Benchmark for AI Co-Scientists in Materials and Battery Research
- Ablating Archetypes: The Stability of Archetypal SAEs is an Artifact of Initialization and Metric Design
- Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning
- From Performance to Viability: A Bootstrap Framework for Latent-Space Representation Learning in Adaptive Biological Systems
- Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention
- A literature-grounded scientific reasoning framework for defect-engineered TiO_{2}_{2} photocatalysts
- Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning
- Detection vs. Execution: Single-Bucket Probes Miss Half the Mamba-2 State Sink
- Positional Encodings Anchor Spatial Structure in Vision Transformers: A Geometric Perspective on Robustness
- Closed-Loop Molecular Design with Calibrated Deference
- Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability
- Unsupervised Pattern Analysis in Japanese Veterinary Toxicology: A Regulatory-Compliant Framework for Cross-Species Risk Assessment
- Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programming
- Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads
- Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers
- Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics
- Wearable Single-Lead ECG Detects Fine-Grained Structural Heart Disease Through Echo-Report Supervision
- Trajectory Geometry of Transformer Representations Across Layers
- Sycophancy Towards Researchers Drives Performative Misalignment
- Ablation-Reversible Heads Don't Transfer: A Stress Test for Mechanistic Role Claims in Transformers
- GPT-Micro: A large language paradigm for accelerated, inexpensive, and thermodynamics-consistent discovery of constitutive models in manufacturing
- Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms
- Biological Reasoning-Informed Regression for Interpretable Regulatory DNA Activity Prediction
- TianJi-Environ: An Autonomous AI Scientist for Atmospheric Environmental Research
- Contribution Weights: A Geometrical Analysis of Self-Attention Transformers
- DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression
- LLM-Mediated Demand Response Coordination in Smart Microgrids
- VFUSE: Virulent Feature Understanding with Sparse autoEncoders
- Interactions Between Crosscoder Features: A Compact Proofs Perspective
- When Attribution Patching Lies: Diagnosis and a Second-Order Correction
- ATLAS: Active Theory Learning for Automated Science
- The Standard Interpretable Model: A general theory of interpretable machine learning to deductively design interpretable methods using Lagrangian mechanics
- Interpretable enzyme function prediction via sparse autoencoder features of ESMC across the microbial protein universe
- Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics
- Impact of Oxygen on DNA Damage Distribution in 3D Genome and its Correlation to Oxygen Enhancement Ratio after High-LET Irradiation
- Transformer Field Theory: A Response-Theoretic Approach to Mechanistic Interpretability
- Layer-Resolved Optimal Transport for Hallucination Detection in NMT and Abstractive Summarization
- Understanding helpfulness and harmless tension in reward models
- When Does Routing Become Interpretable? Causal Probes on Block Attention Residuals
- Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning
- On Pitfalls of \textit{RemOve-And-Retrain}\textit{RemOve-And-Retrain}: Data Processing Inequality Perspective
- Bag of Dims: Training-Free Mechanistic Interpretability via Dimension-Level Sign Patterns
- Scalable Circuit Learning for Interpreting Large Language Models
- Demystifying Variance in Circuit Discovery of LLMs
- Factorized Neural Operators Decompose Dynamic and Persistent Responses
- Learning Hybrid Biophysical Neuron Models with Neural ODEs
- Circuit Tracing in Autoregressive Protein Language Models
- DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing
- HAPI-EP: Towards Hybrid, Adaptive, and Predictive Digital Twins of Cardiac Electrophysiology
- Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning
- Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
- Size Doesn't Matter: Cosine-Scored Sparse Autoencoders
- Transformers Learn the Mestre-Nagao Heuristic
- Rational Sparse Autoencoder
- Compressed Computation is (probably) not Computation in Superposition
- A Low-Rank Subspace Analysis of LLM Interventions
- Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions
- Ten Years of the Stochastic Resonance Model of Tinnitus: From Phantom Perception to Adaptive Sensory Optimization
- The Discrete-Log Clock: How a Transformer Learns Modular Multiplication
- Diagnosing and Repairing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry
- OrthoReg: Orthogonal Regularization for Hybrid Symbolic-Neural Dynamical Systems
- Who Wins the Conflict? Mechanistic Interpretability of Text Bias in Audio LLMs
- Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generation
- Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment
- The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs
- Effects of sparsity and superposition on loss in simple autoencoders
- Beyond AHI: An Interpretable Causal-Discovery-Guided Framework for Sleep Recovery in Connected Health
- Critical Percolation as a Synthetic Data Model for Interpretability
- Decoding the Alzheimer's Continuum: Interpretable Multi-Gate Routing for Diagnosis and Transition Prediction
- Multimodal Concept Bottleneck Models
- Residue-Level Attributions in Protein Language Models Do Not Recover Allergen Epitopes
- Sparse Neuron Ablation Triggers Catastrophic Collapse of the Language Core in Large Vision-Language Models
- Local Causal Attribution of Chain-of-Thought Reasoning
- Beyond Hooking Onto the World: Referential Profiles and the Numerical Structure of LLM Grounding
- A Validation-Gated Mechanistic Account of Suicidality Detection in LLMs
- BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery
- Beyond Importance: Interchange-Sobol Sensitivity Reveals Task-Specific Content Channels in Transformer Components
- DeepBD: A Grounded Agentic Workflow for Variant Prioritization and Diagnosis of Genetic Birth Defects
- The mechanics of anisotropic active plates with applications to cell alignment on curved substrates
- Towards Version-aware Operations and Transaction Memories for Multi-layer MeMo
- Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?
- Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators
- A Reduced Order Model for Emergent Mechanics in Woven Systems
- Emergent Relational Order in LLM Agent Societies: From Collective Affect to Authority Stratification
- AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent
- Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models
- LMs as Task-Specific Knowledge Bases: An Interpretability Analysis
- Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders
- Radical AI Interpretability
- Localizing RL-Induced Tool Use to a Single Crosscoder Feature
- Refusal Lives Downstream of Persona in Chat Models
- Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA
- The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching
- PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding
- Structural functional identifiability and model discovery in differential equation models
- EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures
- How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
- Representational Depth of Evaluation Awareness Shifts With Scale in Open-Weight Language Models
- Symbolic Mechanistic Data Attribution: Tracing Training Influence to Learned Behavioral Policies
- Attribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning
- Mechanistic Personality Analysis of LLMs Steering Personality via Latent Feature Interventions
- Sparse Autoencoders are Capable LLM Jailbreak Mitigators
- Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?
- Deductive Logic in Language Models: Horizontal vs Vertical Reasoning
- Deep Indentation of Hyperelastic Materials Reveals Tip Independent Parabolic Force Depth Response via Strain Energy Delocalization
- An Interaction Language Model: Mechanism Discovery from Statistical Patterns of Physical Interactions
- A Mechanistic Study of Transformers Training Dynamics
- Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation
- Muon as a Residual Connection
- LLM-Guided ODE Discovery and Parameter Inference from Small-Cohort Aggregate Data
- Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol
- Towards Robustness against Typographic Attack with Training-free Concept Localization
- Fast Multi-dimensional Refusal Subspaces via RFM-AGOP
- Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits
- Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability
- Identifiability Limits of Physics-Informed Inference for Spatial Stochastic Dynamics from Static Snapshots
- From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents
- Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders
- Predicting Therapeutic Outcome via Aligning Patient-Specific Knowledge Graph and Gene-Level Perturbation Representations
- Geometry of Ordinal Representations in Language Models
- Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models
- Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources
- Individual Parameters in Weight-Sparse Transformers Appear Interpretable
- MatPhaseBench: A Semantics-Guided Benchmark for Materials Phase Diagrams Understanding
- Induction Heads Interpolate N-Grams
- Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders
- Latent Programming Horizons in Coding Agents
- Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
- How Learning Dynamics Drive Adversarially Robust Generalization?
- Reliable mechanistic operator recovery with biologically-informed neural networks: principles for architecture and optimisation design
- Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning
- From Statistical to Structural Synergy: A Predictability Framework to Quantify the Effects due to High-Order Mechanisms
- Multiplication Beyond Groups: Stratified Fourier Mechanisms in Transformer Circuits
- Dissociating the Internal Representations of Sycophancy in LLMs
- When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities
- Cross-seed explainability using Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoders
- The impact of nonheritable variation in division rates on population growth across environments
- Towards Isolated Interventions via Almost Orthogonal Features in Language Models
- Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability
- Before the Last Token: Diagnosing Final-Token Safety Probe Failures
- Diagnosing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry
- Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs
- Temporal Preference Concepts and their Functions in a Large Language Model
- Which Neurons Detect Malicious Code? A Probing Study of LLM Security Knowledge
- MLPs are Hebbians: Constructing Efficient Fact-Storing MLPs for Transformers
- Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across Scale
- From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery
- Same Compression Principle, Different Geometry: Rate-Distortion Signatures Dissociate Biological and Artificial Visual Systems
- Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias
- Observable Performance Does Not Fully Reflect Adaptive System Organization: A Multi-Level Analysis of Gait Dynamics Under Occlusal Constraint
- AI-Augmented Adaptive Digital Twin Modeling for Brain Tumor Evolution Prediction and Treatment Scheduling
- The Refusal Residue: When Probes Catch Alignment Faking and When They Don't
- RTS Smoother-Guided Learning of Physics-Based Neural Differential Models
- Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control
- Transcoders for Investigating Deception in Language Models
- Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions
- Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models
- Language Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models
- Compartmental Disease Models with Time-Varying Transmission Rates: A Bayesian Generalized Hamiltonian Monte Carlo framework with Applications to COVID-19
- Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence
- Dispersal diversity buffers species vulnerability to local extinction
- What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle Learning
- Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMs
- Can Interpretation Predict Behavior on Unseen Data?
- Emergent Hierarchical Monosemantic Neurons from the Group-Contrastive Forward-Forward Algorithm
- CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability
- Spatially resolved in-situ characterisation of competing martensitic transformation pathways during nanoscratch in 316H Stainless Steel
- Interval and fuzzy physics-augmented neural networks (iPANN and fPANN) for uncertainty quantification and propagation in constitutive modeling
- A Hybrid Framework for Uncertainty Quantification in Partially Observed Dynamic Biological Systems
- OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization
- Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers
- From Noise to Diversity: Random Embedding Injection in LLM Reasoning
- Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry
- What Does Chain-of-Thought Contribute at Probe Time? Evidence for Local Co-Occurrence Activation
- A Mechanistic Perspective and Circuit-Guided Difficulty Metric for Unlearning
- Do LLMs Know Their Vulnerable Scenarios?
- Continuous surrogates versus threshold Boolean networks for modeling Arabidopsis ISR gene regulation
- Inverse Bayesian Inference for Extracting Lesion Dynamics from Longitudinal Spectral CT
- Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models
- Emergent Symbolic Structure in Health Foundation Models: Extraction, Alignment, and Cross-Modal Transfer
- Phase Structure in Rotary Attention: A Spectral Framework for Semantic Continuity and Execution-Boundary Governance
- Emergent Latent-State Computation under Stochastic Volatility
- Beyond the Post Hoc User Study: Modeling Visual Decision-Making with Active Inference
- A Hierarchical Validity-Audit Framework for Neural Mass Models in Simulation-Based Inference: From Observational Coverage to Mechanistic Interpretation
- Can We Trust AI in 6G? Verifiable and Auditable AI-Driven Trustworthy Wireless Networks
- HYVINT: Intensity-Driven Hypergraph Generation with Variational Embeddings
- Information Processing by Neuron Populations in the Central Nervous System: A Theory of the Mathematical Structure of Data and Operations
- Generic Vision and Cross-Attention for Reaction Yield Prediction
- DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning
- Mechanistic bridges from receptors to whole-brain dynamics: mean-field reductions, validity domains, and computational trade-offs
- A Conductance Based Amygdala Model of Threat Processing in Anxiety and Depression
- The production of meaning in the processing of natural language
- Real-time dynamics of the two-step charge-density-wave transition in bulk 1T-TaS_2_2
- Cardiovascular Digital Twins from Physics Based to Data Driven Approaches
- Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models
- Wigner's Friend Paradox Revisited
- LLMs Can Annotate Attribution Graphs
- Sparse Weight Decomposition for Efficient Circuit Extraction
- Curriculum Multiple Shooting for Robust Training of Neural and Universal Differential Equations
- Subliminal Learning is Non-Semantic Distillation
- Transformers Struggle to Use Their Emergent World Models: Revisiting the Tower of Hanoi, and the Illusion of Thinking
- Finding Usable Weight Mechanisms with Tiled SVD
- Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric Data
- MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering
- Can Graph Learning Learn Circuits?
- Control-Diverse Reinforcement Fine-Tuning: Decoupling the Shared Control Bottleneck of RL Post-Training
- Mechanistic Interpretability-Guided Selective Fine-Tuning of Vision-Language Models for Centimeter-Level Flood Depth Estimation
- Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability
- Decoding Transient X-ray Absorption Spectra of Acetylacetone With Multireference Algebraic Diagrammatic Construction Theory
- From Rating Factors to Crash Mechanisms: A Multiscale Causal DAG Framework Linking Motor Insurance and Road Safety
- Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways
- Label-Free Parkinson's Disease Screening from Face and Voice through Mechanistic Interpretability
- Explainability in Practice: A Survey of Explainable NLP Across Various Domains
- Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
- From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop
- Observable-Reduction-Guided Sparse Regression for Partially Observed Active-Quiescent Systems
- Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia
- Decoding Task Progress from VLA Representations
- Data-Efficient and Interpretable Classification of Circulating Tumor Cell Phenotypes in Microfluidic Devices via Deep Learning
- SCOUT: Semantic Concept Discovery for Open-Vocabulary Editing of face Recognition Templates
- Protein Structure Prediction: From Evolutionary Constraints to Generative Modeling
- CulTrace: Tracing Internal Cultural Reasoning in Large Language Models
- Not All Attention Is Equal: A Quantitative Survey of the EEI Trade-off
- DA-RAC: Distance-Aware Calibration of LLM Judges for Trustworthy AI Auditing
- SpIn-ViT: Designing a Sparsity-Induced Vision Transformer That Is Mechanistically Interpretable
- A Tale of Two Pathways to Gompertz Mortality: Reliability and Vitality from an Actuarial Perspective
- Structure-Guided Spatiotemporal Attention Graph Neural Network for Traffic Flow Prediction
- NAST: Improving Negation Handling in Medical Vision-Language Models through Negation-Aware Selective Training
- SPEAR: Structure Property Explainability with Attention Regularization
- Explanation Multiplicity: Circuit-Level Interpretability Evidence Does Not Survive Defensible Analytic Variation
- Inferring Mechanisms from Bits: Promises and Pitfalls of Higher-Order Information in Cognitive Science
- Mechanistic Interpretability of Structure-Aware Numerical Reasoning in LLaMA 3.1 8B
- Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability
- Explaining Intrinsic Moral Self-Correction with Mechanistic Interpretability
- The Intrinsic Dimension of Prompts in Internal Representations of Large Language Models
- Structure is information: structural identifiability mappings for machine learning with partially observed dynamical systems
- Deep Learning Models Also Recall Features
- Bridging Linguistic Structure and Mechanistic Interpretability for Conceptual Interpretation in Language Models
- Grounding Isn't Knowing: Do VLMs Need Object Localization for Spatial Reasoning?
- What AstroPT knows about galaxies, and what that can teach us about LLMs
- Mechanistic Interpretability of Chain-of-Thought Reasoning via Sequential Activation Patching
- Why Does Robustness Reduce Superposition?
- Align, Unify, Suppress, Route: A Coherentist View of Transformer Computation
- The Communication Map of a Transformer
- Finding and using interpretable latents in a neutrino foundation model with sparse autoencoders
- Direct current thermo-mechanical testing: Principles, uncertainty hierarchy, and its role in advanced materials characterisation
- RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons
- Beyond Static Interpretability: Anticipating Post-SFT Mechanisms from Pre-SFT Parameters for Better Tuning
- A Circuit, Not The Circuit: Non-Unique Causal Localisation of the Mamba-2 State Sink
- Mechanistic Circuit Identification for Controllable Data Generation
- Discovering Cross-Language Reasoning Invariance in LLMs with Geometry-Invariant Sparse Autoencoders
- Modality Contribution Score - A Per-Patient Framework for Quantifying the Relative Diagnostic Contribution of Structural MRI and Amyloid PET in Alzheimer's Disease
- Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation
- Not All Eval-Awareness Is Equal: Capabilities Framing Predicts Compliance
- Circuit Condensation: Post-Training that Concentrates a Behavior's Causal Circuit
- Interpreting Latent Protein Language Model Features with Geometric Annotations
- Mode-Specific Dynamics of CO2 Hydrogenation on Copper: The Hidden Role of Molecular Rotation
- Compositional Failure in Audio-Visual LLMs: Late-Layer Prior Dominance Under Cross-modal Conflict
- Load-Bearing Context: The Question Damage Score for Evaluating Context Reliance in Linguistic Reasoning
- Probing Perceptual Priors of MLLMs via Gibbs Sampling with Interpretable Generative Controls
- How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution
- Circuit Discovery Helps Detect LLM Jailbreaking: A Mechanistic Interpretability Study
- Tracing the Latent Threads: A Mechanistic Study of How LLMs Represent and Operationalize Race and Ethnicity Cues
- MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines
- The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal
- Why Are LLM Backdoor Defenses Fragmented? A Feature-Level Explanation with Sparse Autoencoders
- Interpreting and Steering for Safe and Correct Code Generation
- When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs
- Sparse Koopman Autoencoders Identify Local Dynamical Regimes in Multibasin Systems
- A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability
- Causal Interventions Reveal Typologically Organized Syntactic Mechanisms in Multilingual Language Models
- SNF-Bench: Separating Static Drift from Natural Flow in Long-Horizon Fixed-Camera Video Generation
- Pressure-regulated mechanochemistry at lithium metal-sulfide electrolyte interfaces
- S^3martCirc: Self-supervised Smart Circuit Discovery
- From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling
- Interpretable Symptom Vectors for Depression in a Large Language Model
- A mechanistic modeling framework to interpret ACTH stimulation tests across HPA axis adaptation states and glucocorticoid feedback dynamics
- A Circuit for Plural Reference: How LLMs Represent and Retrieve Singular and Plural Entities
- Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving Perturbations
- Large Language Models in Resolving Contextual Knowledge Conflicts
- The Gradient Does Not See Rank: Rank-Indifference in Matrix-CODI on ProsQA
- ObserverBench: Testing Mechanistic Estimates for Intervention and Control
- Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs
- On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing
- PhysSAE: Mechanistic Interpretability with Sparse Autoencoders
- DrugReason: Dynamic Multi-View Reasoning over Knowledge Graph and Language Evidence for Drug Repurposing
- When Does Activation Steering Change What a Model Computes From?
- Covariance Spectrum in Nonlinear Recurrent Neural Networks: A Near-Critical Effective Connection Strength Throughout Chaos
- Capsule Lens: Locating and Tracking Concept Geometry in Model Representations
- SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
- Noise in Diffusion Models Is a Learnable Input
- Medical AI Encodes a "Feeling of Error": Verifying Cancer Segmentation via Internal Concepts
- Autonomous Chemical Mechanistic Discovery through Agentic Reasoning and Validation
- Mixing dynamics and transport mechanisms during laminar stirring flows
- Sparse Weight and Edge Circuit Discovery in Transformer-based Acoustic Models
- Operator-matched spatial regression
- The Misery of Mechanistic Interpretability: A Formal Perspective
- Artificial entrepreneurial cognition: Locating and causally steering an opportunity recognition dial inside large language models (LLMs)
- Sensory Precision Inference for Multimodal Arbitration under Uncertainty
- What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE Track
- PhysSAE: Mechanistic Interpretability of PINNs with Sparse Autoencoders
- Domain-Specific Jargon in Large Language Models: A Comparative Analysis between General-Purpose and Specialist Models
- Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models
- (How) Do MLLMs Report Bistable Images Like Humans?
- There Is More to Refusal in Large Language Models than a Single Direction
- Flag Game: A Toy Model for Mechanistic Swarm Interpretability
- A Four-Stage Decomposition of Word-Problem Solving and Mechanistic Fragility in LLM Math Reasoning
- Reproducing Transparent and Scrutable Recommendations: Exploring Open-Weight Models via Natural-Language User Profiles
- Enhanced Agriculture-informed Neural Network by Domain Knowledge
- World Modeling in Transformers
- Integral chemical reaction neural networks
- Identifying Neural State Changes due to Gain versus Off-Manifold Displacement
- From In Silico to In Vitro: A Comprehensive Guide to Validating Bioinformatics Findings
- Comparing Latent Concept Formation in State Space Models and Transformers via Sparse Autoencoders
- Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity
- Circuit-Diff: Factual Edit-based Intervention Method for Localizing Knowledge in Attribution Graphs
- Quantitative Classical Relaxation Dynamics of Penning-Ionized He/Ne--H_2^+_2^+/HD^+^+ Complexes
- Machine-Interpretable Information: Compiling Documents into Searchable and Readable Protocol States
- How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation
- Look Before You Steer: Geometry Predicts SAE Feature Steerability
- In Vivo Length Distributions as Mechanistic Fingerprints of Pathological Protein Aggregation
- Quantitative Evidence Mining for Plausibility-Aware Biomedical AI: A Narrative Review and Conceptual Framework
- Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in LLMs
- Learning continuous reaction paths for transition-state prediction
- Matryoshka attribution: Learning to attribute language model outputs to representations and weights
Dedicated Publication Threads
Library
Tutorial
Written Tutorials
- Mechanistic Interpretability for LLMs, explained by The CounterFactual
- Zoom In: An Introduction to Circuits (Bilingual Tutorial) - Bilingual (Chinese/English) hands-on Jupyter notebook tutorial reproducing Olah et al. 2020's circuits research, covering feature visualization and mechanistic interpretability in CNNs.
Video Tutorials
Contributing
We welcome contributions to this repository! If you have a resource that you believe should be included, please submit a pull request or open an issue. Contributions can include:
- New libraries or tools related to mechanistic interpretability
- Tutorials or guides that help users understand and implement mechanistic interpretability techniques
- Research papers that advance the field of mechanistic interpretability
- Any other resources that you find valuable for the community
How to Contribute
- Fork the repository.
- Create a new branch for your changes.
- Make your changes and commit them with a clear message.
- Push your changes to your forked repository.
- Submit a pull request to the main repository.
Before contributing, take a look at the existing resources to avoid duplicates.
License
This repository is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). You are free to share and adapt the material, provided you give appropriate credit, link to the license, and indicate if changes were made.
Star History
llms
mechanistic-interpretability
Similar repos
Contributors
Languages
JavaScript
100.0%