© 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. 129577
    Prev
    Next
    INDEX
    Explanations

    Project and business

    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
     Covenant
    -0.28
    åıĭæĥħéĵ¾æİ¥
    -0.27
     /************************************************************************
    -0.25
    ฬ
    -0.25
    CharArray
    -0.24
    .cloudflare
    -0.24
     Gentle
    -0.24
    GRAM
    -0.24
    /{{
    -0.24
     ero
    -0.24
    POSITIVE LOGITS
    è¡Į人
    0.29
    agu
    0.24
    horn
    0.24
    éĽ¢ãĤĮ
    0.24
    avin
    0.24
    ify
    0.24
    çŁ¥æĥħ
    0.24
    itories
    0.24
    ahr
    0.23
     true
    0.23
    Activations Density 17.924%

    No Known Activations