© 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. 20-TRANSCODER-HP
    7. 130850
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wner
    -0.30
    大åŀĭ
    -0.28
    ocab
    -0.28
    Äħc
    -0.25
    ufact
    -0.25
    ä¸ĬæĿ¥
    -0.25
     keras
    -0.24
    .Editor
    -0.24
     registr
    -0.24
    绾
    -0.24
    POSITIVE LOGITS
    ìłĪ
    0.28
    解åĨ³æĸ¹æ¡Ī
    0.28
    á»ĩm
    0.27
    vos
    0.26
    enti
    0.26
    ismatic
    0.26
    ç¢Ľ
    0.25
     sails
    0.25
    VEL
    0.25
    ylvania
    0.24
    Activations Density 90.163%

    No Known Activations

    This feature has no known activations.