© 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. 31-TRANSCODER-HP
    7. 19983
    Prev
    Next
    INDEX
    Explanations

    say "direction"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç¾İæĸ¹
    -0.34
    塾
    -0.29
     americ
    -0.28
     améric
    -0.28
    aat
    -0.26
     USDA
    -0.26
    åľ¨ç¾İåĽ½
    -0.25
    _uc
    -0.25
    客æĪ·æľįåĬ¡
    -0.24
     Americans
    -0.24
    POSITIVE LOGITS
    æ·±
    0.40
     deep
    0.37
    deep
    0.30
    æķ´
    0.29
    POST
    0.28
    深度
    0.28
     Bulgaria
    0.28
     Poland
    0.28
     deeply
    0.28
    ÙĬا
    0.27
    Activations Density 0.982%

    No Known Activations