© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97063
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Negative Logits
    hattan
    -0.28
    ...↵↵
    -0.27
    ilenames
    -0.26
    whelming
    -0.26
    ...↵
    -0.25
    [
    -0.24
    ISBN
    -0.23
    åĩº
    -0.23
    æĢ§ä»·
    -0.23
     Updated
    -0.23
    POSITIVE LOGITS
    .Information
    0.31
    NSS
    0.28
    ä¸ļåĬ¡
    0.27
    vore
    0.26
    ogo
    0.26
    SWG
    0.25
    rens
    0.24
    aÄŁ
    0.24
    ADX
    0.24
    (rad
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.