© 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. 141871
    Prev
    Next
    INDEX
    Explanations

    in

    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
     cé
    -0.27
    ä¾ĽéľĢ
    -0.27
     quote
    -0.27
     quotation
    -0.27
    urer
    -0.24
    两åıª
    -0.24
    avers
    -0.23
    æ¯ķç«Łæĺ¯
    -0.23
     translated
    -0.23
     Mets
    -0.23
    POSITIVE LOGITS
     Pai
    0.26
    asti
    0.25
     pylab
    0.24
    ика
    0.24
    posta
    0.24
    ritable
    0.23
    ishing
    0.23
    iasi
    0.23
     updateTime
    0.23
    æĺ
    0.23
    Activations Density 8.544%

    No Known Activations