© 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. 35-TRANSCODER-HP
    7. 40157
    Prev
    Next
    INDEX
    Explanations

    programming and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stock
    -0.40
    stock
    -0.39
    (stock
    -0.36
     stocks
    -0.33
    èĤ¡ç¥¨
    -0.31
     Stock
    -0.29
     ears
    -0.27
    Stock
    -0.27
    stocks
    -0.26
     stocking
    -0.26
    POSITIVE LOGITS
    occ
    0.36
    oc
    0.33
    oks
    0.31
     Occ
    0.31
    lok
    0.31
    and
    0.30
     GDK
    0.29
     Sadd
    0.28
    bst
    0.27
    orem
    0.27
    Activations Density 0.013%

    No Known Activations