© 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. 42018
    Prev
    Next
    INDEX
    Explanations

    computer code and manuals

    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
    èİ«
    -0.29
    olest
    -0.27
     S
    -0.27
    urgeon
    -0.26
    ceil
    -0.26
    ìĬ¬
    -0.26
    ä¸įåı¯
    -0.25
    osten
    -0.25
     Mongo
    -0.25
    resco
    -0.25
    POSITIVE LOGITS
    (ui
    0.25
    æѤæ¡Ī
    0.24
    å¾ħéģĩ
    0.24
    æĬķæľº
    0.24
    .ide
    0.24
    æĽĿ
    0.24
     mies
    0.23
    åŁŃ
    0.23
    ³»
    0.23
     Bent
    0.23
    Activations Density 0.000%

    No Known Activations