© 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. 31-TRANSCODER-HP
    7. 19610
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    让æĤ¨
    -0.31
    ä¾Ľå¤§å®¶
    -0.31
     observed
    -0.27
    大åѦæ¯ķä¸ļ
    -0.27
    æĤ¬
    -0.27
    è¿ĻéĩĮæľī
    -0.26
    è¿Ļä¸ĢçĤ¹
    -0.25
    åĪ°æĿ¥
    -0.24
    åģļåĩºäºĨ
    -0.24
    æĤ¨
    -0.24
    POSITIVE LOGITS
    icals
    0.29
    kaar
    0.27
    æŀ¹
    0.27
     öde
    0.26
     DAYS
    0.25
    ä¸įå®ļ
    0.25
    --č↵
    0.25
    .invalid
    0.25
     MOST
    0.24
    å¡ŀ
    0.24
    Activations Density 0.073%

    No Known Activations

    This feature has no known activations.