© 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. 19915
    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
    Negative Logits
    åIJĮäºĭ
    -0.26
    imu
    -0.25
    OLID
    -0.25
     Pods
    -0.25
    IR
    -0.25
     Cursor
    -0.24
    å¸Į
    -0.24
     ìķŀìľ¼ë¡ľ
    -0.24
     decks
    -0.24
     folded
    -0.24
    POSITIVE LOGITS
    æ·ĸ
    0.28
    è¿ĻçĤ¹
    0.26
    udd
    0.26
    material
    0.25
    æĢı
    0.25
    .GetBytes
    0.25
    cause
    0.24
    atan
    0.24
    .Manager
    0.24
    entes
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.