© 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. 108472
    Prev
    Next
    INDEX
    Explanations

    computer code/programming

    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
     Brow
    -0.25
    æŃ£éĿ¢
    -0.24
    ẩm
    -0.24
    ka
    -0.23
    iren
    -0.23
     projected
    -0.23
    æĮģå¹³
    -0.23
     ----------------------------------------------------------------------↵
    -0.22
     Middleton
    -0.22
    icks
    -0.22
    POSITIVE LOGITS
    æĺı
    0.27
    seys
    0.26
    ÑĥлÑĮÑĤ
    0.26
    åľ¨æł¡
    0.26
    pch
    0.25
    rer
    0.25
    edList
    0.24
    <*
    0.24
     unwrap
    0.24
    MISSION
    0.24
    Activations Density 0.738%

    No Known Activations