Views
No views yet
| Field | Value |
|---|---|
| Model | Qwen/Qwen2.5-1.5B-Instruct |
| Hook site | blocks.10.hook_resid_post |
| Direction norm (raw) | 11.7328 |
| Source paper | Arditi et al. 2024 |
| Source run | run-000070 |
mech apply-steering --vector refusal-qwen-2.5-1.5b-l10 --coefficient 3.0 --prompt "Your prompt here"1from mech_interp.steering.registry import load_steering_vector
2
3direction, metadata = load_steering_vector("refusal-qwen-2.5-1.5b-l10")masonwyatt23/sv-refusal-qwen-2-5-1-5b| File | Description |
|---|---|
direction.safetensors | Unit-norm direction tensor under key "direction" |
direction.safetensors.json | Extraction metadata sidecar |
bundle_metadata.json | Machine-readable bundle manifest |