© 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. 18-TRANSCODER-HP
    7. 90317
    Prev
    Next
    INDEX
    Explanations

    code/links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    weise
    -0.28
     []↵
    -0.27
    ç»ıå¼Ģ
    -0.26
    åıijå±ķçļĦ
    -0.25
    çī©ä»·
    -0.24
     trúc
    -0.24
     acompaña
    -0.24
     affect
    -0.24
    Fac
    -0.23
     CharSet
    -0.23
    POSITIVE LOGITS
    .proj
    0.31
    å¤§èµĽ
    0.24
     Albums
    0.24
    åı¦ä¸ĢåįĬ
    0.24
    è¿Ļå°±æĺ¯
    0.24
    æľ¬æ¬¡æ´»åĬ¨
    0.24
    -guard
    0.23
    ERY
    0.23
     drown
    0.23
    ä¸Ģåı·
    0.23
    Activations Density 10.655%

    No Known Activations