© 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. 140907
    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
    acic
    -0.28
    bac
    -0.27
     bac
    -0.26
    ören
    -0.26
    getMessage
    -0.26
    è¿ĽåŁİ
    -0.26
     fé
    -0.26
     oy
    -0.25
    TRUE
    -0.25
    ToLocal
    -0.25
    POSITIVE LOGITS
    æİĴè¡Į
    0.30
    以人æ°ij
    0.26
    æ´»è·ĥ
    0.26
    第ä¸ĢæĿ¡
    0.26
    ripple
    0.25
    ç»Ĩèħ»
    0.25
    agra
    0.25
     suff
    0.25
    仪表
    0.25
    yt
    0.25
    Activations Density 5.127%

    No Known Activations

    This feature has no known activations.