© 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. 107614
    Prev
    Next
    INDEX
    Explanations

    code/scripts

    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
    inic
    -0.30
     Warfare
    -0.26
    athing
    -0.25
    æĬĢæľ¯åĴĮ
    -0.25
    oland
    -0.25
    _managed
    -0.25
    __;↵
    -0.24
    rive
    -0.24
    çİ°éĩijæµģ
    -0.24
     пен
    -0.24
    POSITIVE LOGITS
    èľĺèĽĽ
    0.29
     semantic
    0.28
    宪æ³ķ
    0.27
     legal
    0.27
    ç¡Ĵ
    0.26
    å¯Ł
    0.26
    èĽŃ
    0.26
     unknown
    0.26
     four
    0.25
     Garn
    0.25
    Activations Density 71.611%

    No Known Activations