© 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. 130951
    Prev
    Next
    INDEX
    Explanations

    Events evolving over time

    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
    è¿Ľä¸ĢæŃ¥
    -0.27
    éļıçĿĢ
    -0.25
    selling
    -0.24
    -work
    -0.24
    ç¼®
    -0.23
    sav
    -0.23
    à¹Ģà¸Ī
    -0.23
    igkeit
    -0.23
    该åİ¿
    -0.23
    .scal
    -0.23
    POSITIVE LOGITS
     eventually
    0.43
     nowadays
    0.40
    çİ°åľ¨å·²ç»ı
    0.39
     Eventually
    0.39
    æľĢç»Ī
    0.35
    Eventually
    0.34
    缮åīįå·²
    0.34
    å·²æĪIJ为
    0.33
    å·²æĺ¯
    0.33
    å·²ç»ıæĪIJ为
    0.32
    Activations Density 0.012%

    No Known Activations