© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129130
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¢ŀæ·»
    -0.32
    æĶ¹ä¸º
    -0.30
     increasing
    -0.30
    å¢ŀèĩ³
    -0.29
    å¢ŀå¤ļ
    -0.29
    incre
    -0.29
    å¢ŀ大
    -0.28
    Increasing
    -0.28
    æĶ¹åıĺ
    -0.28
    éĻįä½İ
    -0.27
    POSITIVE LOGITS
    æı¡
    0.28
     Nest
    0.27
    åħ¸åŀĭçļĦ
    0.26
    第äºĮ个
    0.25
    æĻļæľŁ
    0.24
    ']),
    0.23
     nest
    0.23
    æģĭ
    0.23
     Rooms
    0.23
     âm
    0.23
    Activations Density 0.007%

    No Known Activations