© 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. 107861
    Prev
    Next
    INDEX
    Explanations

    Place names

    np_max-act · gemini-2.0-flash
    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
    zÄĻ
    -0.27
    èŀºæĹĭ
    -0.26
    æ½ľåľ¨
    -0.25
    çļĦæĪIJåĬŁ
    -0.25
    pany
    -0.25
    rese
    -0.25
    åĨįæĿ¥
    -0.25
    ç¾¹
    -0.24
    e
    -0.24
    è¿ĺæľīä¸Ģ个
    -0.23
    POSITIVE LOGITS
    stück
    0.27
    éŵ
    0.25
    éķ¿å¯¿
    0.25
    lags
    0.25
    ç»ĻæĤ¨
    0.25
    çŁŃ线
    0.25
    è¿ĩ
    0.24
    agit
    0.23
    æĤ¨çļĦåŃ©åŃIJ
    0.23
    colon
    0.23
    Activations Density 5.478%

    No Known Activations