© 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. 64457
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    é¼ĵèĪŀ
    -0.25
    agra
    -0.24
    çĬĬ
    -0.24
    æ¿ĢåĬ±
    -0.24
    agas
    -0.24
    cratch
    -0.24
    icter
    -0.24
    gram
    -0.24
    åľ¨è¿ĩ渡
    -0.24
     sag
    -0.23
    POSITIVE LOGITS
    _IOS
    0.26
    ä¸ŃåĽ½æĸĩåĮĸ
    0.25
     ÑģекÑĢеÑĤ
    0.24
    åĬĪ
    0.24
    INI
    0.24
    ä¸ĢåıĮ
    0.24
    (IConfiguration
    0.24
    ByEmail
    0.23
    æ±Łä¸ľ
    0.23
    约åIJĪ
    0.23
    Activations Density 3.044%

    No Known Activations

    This feature has no known activations.