© 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. 64518
    Prev
    Next
    INDEX
    Explanations

    Letters and numbers

    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
    ilon
    -0.35
    秣
    -0.31
     medida
    -0.28
     thereafter
    -0.27
    beb
    -0.26
    thed
    -0.25
    ç½ijä¸Ĭ
    -0.25
    거리
    -0.25
     safeguard
    -0.25
    .SEVER
    -0.24
    POSITIVE LOGITS
    æĭ¥æĬ¤
    0.27
    patches
    0.26
     directors
    0.25
     director
    0.24
    orp
    0.24
    纯
    0.24
    ä¹Łè¢«
    0.24
    cre
    0.24
    导æ¼Ķ
    0.23
    -direct
    0.23
    Activations Density 2.601%

    No Known Activations