What the J Lens Protocol Isolates That a Logit Lens Cannot
August 15, 2026
No Comments
Isolate causal paths and confirm necessity on residual streams with the J Lens joint lens and first-order Jacobian stack.
AI interpretability · Jacobian Lens · alignment
How language models think — made legible.
Research explainers on J-Space and the internal workspaces where modern LLMs stage reportable reasoning.
Featured · AI Safety
Safety teams decode models with mechanistic interpretability
How safety teams use interpretability to catch behaviors that tests miss — and make model behavior operational.
Read featured explainer →All explainers
Deep dives on Anthropic’s interpretability work, internal workspaces in LLMs, and what J-Space reveals about model behavior.
Tracing Causal Paths in Claude’s Addition and Safety Circuits
August 14, 2026
No Comments
Researchers map how features causally influence Claude outputs by reconstructing prompt specific graphs with sparse autoencoders and cross layer…
Sparse Autoencoders Use L1 Penalties to Isolate Distinct Model Features
August 10, 2026
No Comments
Sparse autoencoders use L1 penalties on residual activations to generate sparse mostly zero latents that correspond to candidate features in language…
Safety Teams Decode AI Models Using Mechanistic Interpretability in 2026
August 2, 2026
No Comments
Safety teams use mechanistic interpretability to reveal AI behaviors missed by tests, making safety operational in 2026.
Latent Correctness Directions Emerge from Residual Activations Without Probes
August 1, 2026
No Comments
Latent correctness directions appear in residual activations of language models when using Jacobian lenses and sparse autoencoders instead of probes.
How J-space Detects Model Misalignment
July 25, 2026
No Comments
In brief J-space detects model misalignment by examining a compact internal workspace in large language models that handles deliberate reasoning, using the…
A research lens on internal model cognition
J-Space tracks the sparse internal workspace where language models stage reportable reasoning. The Jacobian Lens makes that workspace measurable — so safety, alignment, and interpretability research can move from speculation to evidence.