A browser tool that reads a model's internal concepts layer by layer before it speaks, using the Jacobian lens

Show HN: I built a web tool to see and edit what an AI thinks before it answers

Lucid lets you type a prompt in the browser and watch which concepts activate inside small models like Qwen and Pythia before they answer, layer by layer. It uses a Jacobian lens that costs a single forward pass, no account or install needed. The author borrows Anthropic's J-space framing, treating the model's reportable internal representations as a global workspace. Zener cards serve as a demo: the lens reads the answer four layers before the model speaks. Currently only 0.5B–3B open models are supported; the post doesn't say when larger models will be added.

Why it matters: Turns interpretability research into a browser tool that reads internal concepts from small models via Jacobian lens — specific models, reproducible demo, hits all three HKR axes. Score held back because it only works on small models and is far from production; it's a polished...