© 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. 31-TRANSCODER-HP
    7. 19163
    Prev
    Next
    INDEX
    Explanations

    Ham

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     figure
    -0.27
    pository
    -0.26
     figures
    -0.26
    ç¥
    -0.24
     mess
    -0.24
    çݯ
    -0.24
    à¹Ģà¸Ńา
    -0.23
    éĽĨä½ĵ
    -0.23
    lossen
    -0.23
     Took
    -0.23
    POSITIVE LOGITS
    erts
    0.27
     manh
    0.26
     Bomb
    0.26
    è¾ĭ
    0.26
    ç»Ħç»ĩå®ŀæĸ½
    0.26
    èĬĿ麻
    0.25
    Invocation
    0.25
    ãĤ¹ãĤ¿ãĥ¼
    0.25
    spar
    0.25
    oglob
    0.25
    Activations Density 0.265%

    No Known Activations