wangzhang/Qwen3.5-122B-A10B-abliterated-v1
Image-Text-to-Text • 123B • Updated
• 156 • 7
Steve Wu PRO
wangzhang
AI & ML interests
Neural Network Interpretability, Refusal Direction Analysis, LLM Safety Mechanisms, Model Abliteration Techniques, Activation Engineering, AI Alignment Research, Mixture-of-Experts Architectures, Transformer Optimization
Recent Activity
new activity
about 23 hours ago
wangzhang/Qwen3.5-122B-A10B-abliterated-v1:v2 now available: Qwen3.5-122B-A10B-abliterated updated
a model about 23 hours ago
wangzhang/Qwen3.5-122B-A10B-abliterated-v1 liked
a model 1 day ago
wangzhang/Qwen3.5-0.8B-abliterated Organizations
None yet
wangzhang/Qwen3.5-35B-A3B-abliterated
Image-Text-to-Text • 35B • Updated
• 26 • 2
wangzhang/Qwen3.5-9B-abliterated
Image-Text-to-Text • 9B • Updated
• 37 • 2
wangzhang/Qwen3.5-0.8B-abliterated
Text Generation • 0.9B • Updated
• 51 • 1
wangzhang/GLM-4.7-Flash-abliterated
30B • Updated
• 49 • 2
wangzhang/MiniMax-M2.5-abliterated
229B • Updated
• 12 • 4