© 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. 131158
    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
    omen
    -0.25
    ibbon
    -0.25
    urry
    -0.24
    ystery
    -0.23
    à¸Ļาà¸Ļ
    -0.22
     race
    -0.22
     rac
    -0.22
    ìĿ´ëĿ¼
    -0.22
    -bs
    -0.22
    trust
    -0.22
    POSITIVE LOGITS
    <HTML
    0.23
     *&
    0.23
     rule
    0.23
    _rule
    0.23
    ç¢İ
    0.23
    ä¸İä¼Ĺ
    0.23
     unsuccessfully
    0.23
     Rule
    0.23
    rule
    0.22
     interchange
    0.22
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.