© 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. 108263
    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
    cit
    -0.30
    <[
    -0.27
    ersen
    -0.27
    ULA
    -0.26
    à¸Ńà¸Ńà¸ģà¹Ħà¸Ľ
    -0.26
    ula
    -0.25
    pton
    -0.25
    ToDate
    -0.25
    纳æĸ¯
    -0.25
    áĢĬ
    -0.25
    POSITIVE LOGITS
    snap
    0.30
    renom
    0.29
     snaps
    0.28
    æľĢæĸ°
    0.28
     whichever
    0.27
    eler
    0.27
    ssc
    0.27
    lesson
    0.26
    uss
    0.26
     Magnum
    0.26
    Activations Density 12.970%

    No Known Activations

    This feature has no known activations.