© 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. 12-TRANSCODER-HP
    7. 23876
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dtype
    -0.31
    大家
    -0.30
    大家åı¯ä»¥
    -0.28
    Proceed
    -0.27
    ermann
    -0.27
    ucken
    -0.26
     tipping
    -0.25
    çļĦæłĩåĩĨ
    -0.25
    oidal
    -0.25
    ç¡İ
    -0.25
    POSITIVE LOGITS
    Injected
    0.27
    èıĺ
    0.27
    apon
    0.26
    ä¿Ŀå®Ī
    0.25
    -an
    0.25
    -sdk
    0.24
    éĴ¢æĿ¿
    0.24
    tÃł
    0.24
    ToLocal
    0.24
    éĺ²æ°´
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.