© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129445
    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
    ä¹Łä¸įè¦ģ
    -0.27
    (bind
    -0.26
    Insert
    -0.25
    ä»ĸä¹Ł
    -0.25
    getC
    -0.24
    è¼ķ
    -0.24
     lẫn
    -0.24
    ideos
    -0.24
    æľĪ以æĿ¥
    -0.23
    .Insert
    -0.23
    POSITIVE LOGITS
    人çļĦ
    0.27
    é¼ĵ
    0.27
    æĹ¢æĺ¯
    0.26
    ito
    0.25
    obia
    0.25
    .paging
    0.25
    uating
    0.24
    berman
    0.24
    离
    0.24
    éģ¿
    0.24
    Activations Density 65.288%

    No Known Activations

    This feature has no known activations.