@AnthropicAI: We also partnered with Neuronpedia to create an interactive demo of our methods on open-weights models. Try it here:

X AI KOLs Tools

Summary

Anthropic partnered with Neuronpedia to release an interactive demo of their interpretability methods on open-weights models, called Jacobian Lens.

We also partnered with Neuronpedia to create an interactive demo of our methods on open-weights models. Try it here: https://t.co/hkmYl0IOn2
Original Article
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

Privacy & TermsBlogGitHubSlackTwitterContact

Similar Articles

Anthropic found a hidden space where Claude puzzles over concepts

MIT Technology Review

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.