© 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. 22-TRANSCODER-HP
    7. 130950
    Prev
    Next
    INDEX
    Explanations

    descriptive and instructional text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¶ĵéģİ
    -0.34
    ç»ıè¿ĩ
    -0.34
    ç»ıè¿ĩå¤ļå¹´
    -0.30
     translated
    -0.29
    ç²¾å¿ĥ
    -0.29
    åĬªåĬĽ
    -0.28
    è¯ij
    -0.27
     Undert
    -0.27
    ç¿»è¯ij
    -0.27
     curated
    -0.26
    POSITIVE LOGITS
    åħ·æľīä¸Ģå®ļ
    0.30
    éĿ¢çĽ®
    0.27
    åıªåī©
    0.27
    å±¹
    0.25
    åħ¨æµģç¨ĭ
    0.25
    æĪIJ为ä¸ŃåĽ½
    0.24
    æľįåĬ¡æ°´å¹³
    0.24
    è¿ĿèĥĮ
    0.24
    *pow
    0.23
    ï¼Įé»ĺ认
    0.23
    Activations Density 0.015%

    No Known Activations