© 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. 108004
    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
    ä¾ĭè¡Į
    -0.27
    好çİ©
    -0.26
    roat
    -0.25
    åħ´å¥ĭ
    -0.25
    esk
    -0.25
    oons
    -0.24
    éĩĮæĸ¯
    -0.24
    åĨł
    -0.24
     Freund
    -0.24
    ä¸įå¾Ĺä¸į
    -0.24
    POSITIVE LOGITS
     Budget
    0.25
     elim
    0.25
    她们
    0.25
     Downs
    0.24
    imeo
    0.24
     trump
    0.24
    |m
    0.24
    nore
    0.23
     stronger
    0.23
     downs
    0.23
    Activations Density 31.176%

    No Known Activations

    This feature has no known activations.