© 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. 23-TRANSCODER-HP
    7. 24194
    Prev
    Next
    INDEX
    Explanations

    code/math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŁ·
    -0.32
    uzu
    -0.26
    ãģ¾ãģĹãģ¦
    -0.25
    Friendly
    -0.25
    人家
    -0.24
    HEME
    -0.24
    oped
    -0.23
    oku
    -0.23
    plash
    -0.23
     Jets
    -0.23
    POSITIVE LOGITS
    ä¹Łæĺ¯
    0.85
     also
    0.84
     ÑĤоже
    0.83
    åIJĮæł·
    0.73
    also
    0.72
     ebenfalls
    0.71
    åIJĮæł·æĺ¯
    0.68
    ä¹ŁåIJĮæł·
    0.68
    ä¹Łæĺ¯ä¸Ģç§į
    0.68
     Also
    0.66
    Activations Density 0.004%

    No Known Activations