© 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. 20-TRANSCODER-HP
    7. 128978
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    axe
    -0.28
     rent
    -0.27
    MV
    -0.26
    ç´¯
    -0.26
    atches
    -0.26
     çı
    -0.26
    éĤ£ä¸ªæŶåĢĻ
    -0.25
    ixe
    -0.25
    rage
    -0.24
    mol
    -0.24
    POSITIVE LOGITS
    ...')↵
    0.29
    ONUS
    0.29
    éĢıæĺİ
    0.28
    ...)↵
    0.27
    conditionally
    0.27
    èµį
    0.26
    ...'↵
    0.26
    ...)
    0.25
    忽çķ¥
    0.24
    \Config
    0.24
    Activations Density 0.399%

    No Known Activations