© 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
    2. Qwen3-4B
    3. 22-TRANSCODER-HP
    4. 88202
    Prev
    Next
    INDEX
    Explanations

    race

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -Jun
    -0.27
    utzer
    -0.25
    recio
    -0.25
     Rafael
    -0.25
    elson
    -0.24
    _cmos
    -0.24
    ichern
    -0.24
    ï¼ŁãĢį
    -0.24
    ehler
    -0.24
    dued
    -0.23
    POSITIVE LOGITS
     asc
    0.28
    ³³³³
    0.27
    -time
    0.27
     cá»Ńa
    0.27
    ³³
    0.27
    conf
    0.27
     mean
    0.26
    jump
    0.26
     identity
    0.26
     atl
    0.25
    Activations Density 1.096%

    No Known Activations