@AnthropicAI: We also partnered with Neuronpedia to create an interactive demo of our methods on open-weights models. Try it here:
Summary
Anthropic partnered with Neuronpedia to release an interactive demo of their interpretability methods on open-weights models, called Jacobian Lens.
View Cached Full Text
Cached at: 07/06/26, 06:18 PM
We also partnered with Neuronpedia to create an interactive demo of our methods on open-weights models.
Try it here: https://t.co/hkmYl0IOn2
Jacobian Lens
Source: https://www.neuronpedia.org/jlens © Neuronpedia 2026
Similar Articles
@arafatkatze: Inspired by Anthropic's JSpace paper, we @cline used @modal to host a public demo so anyone can watch a Jacobian-lens v…
A public demo of a Jacobian-lens view of language model representations, inspired by Anthropic's JSpace paper, allowing users to explore model internals across layers and tokens.
@julien_c: Anthropic releasing open source demos built on top of Qwen (with @neuronpedia) is not something that I was expecting
Anthropic releases open source interactive demos built on top of Qwen models, in partnership with Neuronpedia.
@AnthropicAI: To support other researchers getting hands-on experience with NLAs, we’ve partnered with Neuronpedia to release NLAs on…
Anthropic and Neuronpedia have partnered to release Natural Language Autoencoders (NLAs) on open models, allowing researchers to gain hands-on experience with this interpretability tool.
I tested Anthropic’s new Jacobian Lens on open models, then it turned into a local-model hallucination router
The author tested Anthropic's Jacobian Lens on open models, then it evolved into a local-model hallucination router for detecting AI hallucinations.
Anthropic found a hidden space where Claude puzzles over concepts
Anthropic developed the Jacobian lens (J-lens) to reveal a hidden 'J-space' inside Claude Opus 4.6, offering unprecedented insight into an LLM's internal reasoning process before it outputs tokens. The technique allows monitoring and control of model behavior by surfacing the words the model is about to produce.