Shadowgraph
About
Sign in
← Explore by area

Cluster 454351

5 repos

Jupyter Notebook · 2
Python · 1
mechanistic-interpretability ·9
sparse-autoencoder ·9
reasoning-language-models ·5
reasoning ·5
benchmark-datasets ·4
llm-evaluation ·0
linear-probe ·0
hallucination-detection ·0
faithfulness ·0
safety ·0

Related clusters

Neural Network Mechanistic Interpretability14Cluster 45497828Sparse Autoencoders and Mechanistic Interpretability12MLX framework for Apple Silicon ML22Cluster 4475716Math, Code, and Reasoning in LLMs36

GeorgeMLP/reasoning-probing

Official code for ICML 2026 paper "Do Sparse Autoencoders Identify Reasoning Features in Language…

Python

5

103 commits

caiovicentino1/FabricationGuard-linearprobe-qwen36-27b

Dataset

No description

0

10 commits

Yusen-Peng/CE-Bench

[EMNLP-W 2025] CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of…

Jupyter Notebook

4

124 commits

caiovicentino1/ReasoningGuard-linearprobe-qwen36-27b

Dataset

No description

0

4 commits

crate-lm/crate-lm

Official Repository of the Paper "Improving Neuron-level Interpretability with White-box Language…

Jupyter Notebook

6

15 commits