© 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. 12-TRANSCODER-HP
    7. 21942
    Prev
    Next
    INDEX
    Explanations

    sock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    erman
    -0.32
     kiá»ĩn
    -0.29
     feasibility
    -0.28
    çļĦæĥ³æ³ķ
    -0.26
     pole
    -0.26
     æĢ
    -0.26
    icorn
    -0.26
    adelphia
    -0.26
    ило
    -0.26
    ousse
    -0.25
    POSITIVE LOGITS
    å¥¹åľ¨
    0.33
    榻
    0.33
    æĥļ
    0.30
    ä»ĸä»¬åľ¨
    0.26
    éĺ¿æĭī伯
    0.26
    åı¯æĥ³
    0.26
    æĬĦè¢Ń
    0.26
    åĩłæ¬¡
    0.25
    åīįæĸ¹
    0.25
    èº²åľ¨
    0.24
    Activations Density 0.007%

    No Known Activations