Havuz

A catalog of every MLP neuron and attention head of Qwen3-8B and Gemma 4 12B, read from the weights through two Jacobian lenses (R and S), f

Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous

Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interven

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.

To know what models don't say out loud.

OpenAI-compatible server with a live view into any HF model's residual stream. pip install brainscope

AI Systems as Scientific Instruments for Understanding the Mechanisms of Intelligence

Cross-architecture LLM internal observation database (23 models, 13 architecture families). Exposed as MCP tools for any AI coding agent.

Agents that talk through model internals — activations & J-space — instead of text. No words pass between them. The lab on top of brainscope

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking cur

Is there one workspace, or twin workspaces? Testing cross-lingual generalization of the J-space / global workspace in language models.

3D explorable atlas of every neuron in a transformer LLM. Click neurons, trace residual highways, compare cross-architecture conservation. L

Mechanistic experiments on how LLMs represent and compute arithmetic internally, with strict no-parser controls, reproducible audits, and an