© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141843
    Prev
    Next
    INDEX
    Explanations

    Parentheses and punctuation

    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
    jos
    -0.28
    .ArgumentParser
    -0.26
    wend
    -0.26
    è´µ
    -0.25
    æł¼
    -0.25
    adt
    -0.25
    igers
    -0.23
    adan
    -0.23
    缼
    -0.23
    orage
    -0.23
    POSITIVE LOGITS
     пÑĢиÑĩ
    0.27
    quÃŃ
    0.26
     Liberties
    0.26
    =head
    0.25
    llum
    0.25
    β
    0.25
    åı£ä¸Ń
    0.25
     outing
    0.25
    æĮīæŶ
    0.25
    ç¨Ĺ
    0.24
    Activations Density 4.155%

    No Known Activations