© 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. 32-TRANSCODER-HP
    7. 43462
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ìĦ¬
    -0.29
    ât
    -0.27
    ption
    -0.25
    ull
    -0.24
    owied
    -0.24
    éģĽ
    -0.24
    侧éĿ¢
    -0.24
    ,copy
    -0.23
    ç²¾ç¥ŀ
    -0.23
     whole
    -0.23
    POSITIVE LOGITS
    è¾IJ
    0.28
    æµģæ°´
    0.28
    æĮĩæľĽ
    0.27
    ç¥Ń
    0.25
    ima
    0.24
    åŃ³
    0.24
    æĤ¬å¿µ
    0.24
    天èĬ±æĿ¿
    0.24
     Gar
    0.24
     Penalty
    0.24
    Activations Density 0.005%

    No Known Activations