© 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. 25-TRANSCODER-HP
    7. 109354
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¦Ĩ
    -0.29
    ä¸ĢæľŁ
    -0.28
    æ§ģ
    -0.27
    rape
    -0.26
     spiral
    -0.26
    prend
    -0.26
     Fowler
    -0.24
    -flex
    -0.24
     Curtain
    -0.24
    ordion
    -0.24
    POSITIVE LOGITS
    %
    0.29
    è¿Ľåı£
    0.26
     %
    0.26
     introduced
    0.26
     stated
    0.25
     migr
    0.25
    Prof
    0.24
    ç«Ļèµ·æĿ¥
    0.24
     #%
    0.24
    Info
    0.24
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.