© 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. 108516
    Prev
    Next
    INDEX
    Explanations

    Comment symbols

    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
    Negative Logits
    -bound
    -0.29
    ç±į
    -0.28
    inis
    -0.26
    ÊĮ
    -0.24
    FirstChild
    -0.24
    á»Ī
    -0.24
    港åĮº
    -0.23
    union
    -0.23
    Theory
    -0.23
     communities
    -0.23
    POSITIVE LOGITS
    dea
    0.26
    :<
    0.26
    ropriate
    0.25
    flamm
    0.24
    ï¼ļ<
    0.24
    :${
    0.24
    ï¼ļ"
    0.24
    :$
    0.24
    |"
    0.24
    ."+
    0.24
    Activations Density 3.534%

    No Known Activations