neuronpedia/jacobian-lens

Model

106

stars

commits

repos using this model

linked in READMEs

Aug 20, 2026

updated

jacobian_lens

README

This folder contains pre-fitted Jacobian Lenses for specific models. They were trained using Anthropic's Jacobian Lens library. The same library can be used to load the lens and local visualizer.

Jacobian Lens can be explored on Neuronpedia at https://neuronpedia.org/jlens.

license: mit

Contributors

7 commits

5 commits

2 commits

1 commits

Similar repos

idhantgulati/j-lens

minimal J-lens / J-space implementation and visualization (Gurnee et al., 2026) on qwen3.5-4B

anthropics/jacobian-lens

Companion code for the global workspace interpretability paper

1,884

mhough/olmo3-jacobian-lenses

Model

cooelf/vision_features

Model

TransformerLensOrg/TransformerLens

A library for mechanistic interpretability of GPT-style language models

3,864

snap-research/alphaflow

Model

OliverHuang1998/3DRS

Model

mamba413/L2D

Model

Used in code

lolismek/j-think

latent / soft thinking limited to the workspace

3 files

hijohnnylin/neuronpedia

open source interpretability platform 🧠

1,133

2 files

ninjahawk/Subtext

To know what models don't say out loud.

242

2 files

TransformerLensOrg/TransformerLens

A library for mechanistic interpretability of GPT-style language models

3,864

1 file

Extraltodeus/J-Wash

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's…

229

1 file

idhantgulati/j-lens

minimal J-lens / J-space implementation and visualization (Gurnee et al., 2026) on qwen3.5-4B

1 file

Linked in READMEs

anthropics/jacobian-lens

Companion code for the global workspace interpretability paper

1,884

README badge

ninjahawk/Subtext

To know what models don't say out loud.

242

README badge

Extraltodeus/J-Wash

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's…

229

README badge

Liberation-Labs-THCoalition/Project-Mnemosyne

README badge

Azazel5/Bizzaro-World

Utilizing principles of mechanistic interpretability to determine how a transformers works,…

README badge

neuronpedia/jacobian-lens

Model

106

stars

commits

repos using this model

linked in READMEs

Aug 20, 2026

updated

jacobian_lens

README

This folder contains pre-fitted Jacobian Lenses for specific models. They were trained using Anthropic's Jacobian Lens library. The same library can be used to load the lens and local visualizer.

Jacobian Lens can be explored on Neuronpedia at https://neuronpedia.org/jlens.