© 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. 62889
    Prev
    Next
    INDEX
    Explanations

    my

    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
    inals
    -0.33
    imity
    -0.29
    ETY
    -0.28
    eli
    -0.28
    ä¸įåı¯éģ¿åħį
    -0.27
    ainty
    -0.26
    akit
    -0.25
    ãģªãģĦãģ¨
    -0.25
    LEE
    -0.24
    .qual
    -0.24
    POSITIVE LOGITS
    è¿ĩå¾Ĺ
    0.31
     exchange
    0.29
     dissolved
    0.27
     exchanged
    0.24
    down
    0.24
     exchanges
    0.24
    Ups
    0.24
    æĮģç»Ń
    0.24
    ked
    0.23
    éĩį度
    0.23
    Activations Density 33.448%

    No Known Activations