© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 108466
    Prev
    Next
    INDEX
    Explanations

    code copyright notices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿ¡è¯Ħ论
    -0.29
    inem
    -0.28
    请çĤ¹åĩ»
    -0.25
    ÑĤиÑĢов
    -0.25
     inputValue
    -0.24
    etsy
    -0.23
    _strike
    -0.23
    /calendar
    -0.23
    ety
    -0.22
    æļĤ
    -0.22
    POSITIVE LOGITS
    —
    0.26
     covering
    0.24
    Ø´ÙĨ
    0.24
     circulated
    0.24
    —to
    0.23
    —a
    0.23
    ä¸įåİ»
    0.23
     enn
    0.23
    ä¸ĢæīĢ
    0.23
    éıĸ
    0.23
    Activations Density 0.087%

    No Known Activations