bedderautomation/qwen25-3b-abliterated
1 quantizations
trained on 1 dataset 1 in /datasets
↓ 127
♥ 2
AUTHOR
1 model in the catalog. 127 total downloads. First seen 2026-08-22, last activity 2026-08-22. Also publishes 2 alignment datasets (885 downloads).
Alignment datasets by
Datasets this account has published in categories the catalog tracks: extraction pairs, ablation corpora, healing preference sets, evaluation benchmarks, uncensored SFT corpora, and related material. Category badges link to the workflow stage.
Dataset
Stage
Downloads
Likes
refusal-geometry-qwen25-3b 0 0
Refusal Geometry: Qwen2.5-3B-Instruct
Direct measurement of refusal direction geometry extracted via OBLITERATUS analysis pipeline.
Model...
652
-
mechanistic-interpretability-skills 0 0
Mechanistic Interpretability Skills for Claude Code
The first skill set for LLM refusal geometry extraction, boundary surface mapping, an...
233
1
Dataset
Stage
Downloads
Likes
mechanistic-interpretability-skills 0 0
Mechanistic Interpretability Skills for Claude Code
The first skill set for LLM refusal geometry extraction, boundary surface mapping, an...
233
1
refusal-geometry-qwen25-3b 0 0
Refusal Geometry: Qwen2.5-3B-Instruct
Direct measurement of refusal direction geometry extracted via OBLITERATUS analysis pipeline.
Model...
652
-
Dataset
Stage
Downloads
Likes
mechanistic-interpretability-skills 0 0
Mechanistic Interpretability Skills for Claude Code
The first skill set for LLM refusal geometry extraction, boundary surface mapping, an...
233
1
refusal-geometry-qwen25-3b 0 0
Refusal Geometry: Qwen2.5-3B-Instruct
Direct measurement of refusal direction geometry extracted via OBLITERATUS analysis pipeline.
Model...
652
-