© 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. 32-TRANSCODER-HP
    7. 44021
    Prev
    Next
    INDEX
    Explanations

    district/courts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    stell
    -0.30
    åŃ¦æľ¯
    -0.29
     Eighth
    -0.27
    linky
    -0.27
    ington
    -0.27
     Kas
    -0.26
    _fps
    -0.24
    erties
    -0.24
    ernity
    -0.24
    emes
    -0.24
    POSITIVE LOGITS
    å¿ĥåĬ¨
    0.29
     lá
    0.26
    vent
    0.26
    ç«Ļç«ĭ
    0.25
    zia
    0.25
    å©ļ礼
    0.25
    Ether
    0.25
    æ±Łä¸ľ
    0.25
     sacrificed
    0.25
    ITU
    0.25
    Activations Density 0.002%

    No Known Activations