Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

AlignmentResearch
/
probe-inference-weights

probes
activation-probes
interpretability
Model card Files Files and versions
xet
Community
probe-inference-weights / qwen3.5-2b /linear
66.8 kB
Ctrl+K
Ctrl+K
  • 3 contributors
History: 3 commits
chrisjcundy's picture
chrisjcundy
Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12
05def1c verified about 8 hours ago
  • layer_10
    Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12 about 8 hours ago
  • layer_13
    Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12 about 8 hours ago
  • layer_16
    Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12 about 8 hours ago
  • layer_19
    Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12 about 8 hours ago
  • layer_22
    Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12 about 8 hours ago
  • layer_7
    Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12 about 8 hours ago
  • probe_metadata.json
    345 Bytes
    Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12 about 8 hours ago