A Jacobian-Lens (J-Lens) observer for vision-language models — read what a VLM is poised to say, before it says it. Multimodal J-Lens on Qwen3.5, concept-race, and a forward-only prompt helper.

Find the layer where a language model commits a decision — and steer it. Any open-weight HF model. (WANDERING arc paper #6)

Open-source EU AI Act Annex IV documentation toolkit. Mechanistic interpretability + circuit discovery for transformers. One function call generates a structured, hash-chained evidence package.

OKI TRACE: Local LLM observability. See step-by-step, layer-by-layer what your AI thinks. Logit Lens & Attention for HuggingFace models.

A J-space-inspired AI visual art and interpretability playground for watching hidden-state word candidates swarm and collapse into language.

Watch a language model's thoughts form before it speaks — interactive workbench + findings for Anthropic's Jacobian lens

Decoding the black box of LLMs: A comparative analysis of Logit Lens vs. Tuned Lens to interpret intermediate Transformer layers in GPT-2.

🏛️ Champollion cracked hieroglyphs in 1822. I applied the same logic to LLM internals. 95% accuracy, $0 cost, fully reproducible. Contributors welcome.

Mechanistic interpretability CLI for transformer models on Apple Silicon. Analyze per-layer predictions, monitor activation drift, compare models, discover circuits. MLX-based, no GPU needed.

Mechanistic interpretability experiments for transformer language models built from scratch in JAX/Flax. Investigates internal representations using Logit Lens, Activation Patching, and Sparse Autoencoders (SAEs) to understand how information flows through transformer layers.

Local Streamlit app for mechanistic interpretability of transformer models.

From-scratch PyTorch implementation of the Tuned Lens (Belrose et al., 2023) — learned per-layer affine probes that sharpen intermediate transformer predictions beyond the raw logit lens.

A small, extensible mechanistic-interpretability lab — logit lens & activation patching on GPT-2 and Qwen3 behind a unified backend adapter. Config-driven, tested, laptop-friendly.

Watch a live LLM think — real-time attention, logit-lens predictions, and token probabilities. Type a prompt, export a shareable X-ray card.

Local web playground to look inside Qwen3-0.6B: logit lens, attention maps, activation steering, chat, image gen

Mechanistic-interpretability experiments for visualizing and manipulating Qwen reasoning

CLI toolkit for logit-lens analysis, neuron discovery, and activation steering

Sparse Readout Prism: a sparse LM-head basis for logit-lens readouts — companion code for the paper. Pretrained dictionaries: hf.co/hematteo/sparse-readout-prism

In-browser LLM interpretability: from-scratch logit lens and activation steering on WebGPU

Logit Lens terminal visualizer (nostalgebraist, 2020) — decodes GPT-2's intermediate layer predictions using the unembedding matrix, built with TransformerLens and Rich.