Running on Zero Agents NLA v3 — Activation Explorer 🔬 Click a token, read its activation in plain English
Matryoshka NLA (Qwen2.5-7B L20) Collection An NLA trained with random-length truncation of the verbalizer's output, so the most important information comes first. Checkpoints, data, baseline. • 8 items • Updated 2 days ago
Running on Zero Agents NLA v3 — Activation Explorer 🔬 Click a token, read its activation in plain English