© 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. 141681
    Prev
    Next
    INDEX
    Explanations

    scientific/technical writing

    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
    SRC
    -0.30
     Nazi
    -0.28
     Src
    -0.27
     src
    -0.26
    è¿ľæĻ¯
    -0.26
    æľīèī²
    -0.26
    é¦Ĩ
    -0.25
    TECT
    -0.25
    ä¸Ģ
    -0.25
    LL
    -0.25
    POSITIVE LOGITS
    ...");č↵
    0.27
    =nil
    0.27
     improvis
    0.24
    sla
    0.24
    çļĦæł·åŃIJ
    0.24
    èĽ©
    0.24
    éĢij
    0.24
    çļĦä¸Ģ项
    0.24
     Holt
    0.24
     yourselves
    0.24
    Activations Density 39.874%

    No Known Activations