@metaharness/workspace-lens
MITJacobian-Lens interpretability primitive for open-weight LLMs (Anthropic 2026-07-06, 'Verbalizable Representations Form a Global Workspace'). Reads the model's functional workspace at inference time — lens_l(h)=unembed(J_l·h) — into workspace tokens, laye
100
Security score
0 known advisories in v0.1.2
Weekly downloads
—
Unpacked size
63.6 kB
Dependencies
0
Last publish
21 hours ago
Security advisories
No known vulnerabilities affect v0.1.2.