© 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. 108525
    Prev
    Next
    INDEX
    Explanations

    Beginning of documents

    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
    çļĦæ¯Ķä¾ĭ
    -0.27
    æĺı
    -0.26
    Susp
    -0.26
    Attention
    -0.25
    为主çļĦ
    -0.25
    ائÙĬ
    -0.24
    å¹ķåIJİ
    -0.24
    æ¯Ķä¾ĭ
    -0.24
     amounts
    -0.24
    bons
    -0.24
    POSITIVE LOGITS
    ä»ĸ们æĺ¯
    0.27
    MMC
    0.25
    åĩºéģĵ
    0.25
    ä¸ŃåĽ½æ¢¦
    0.25
    (vol
    0.24
    ä»ĸ们ä¼ļ
    0.24
     metaData
    0.24
    ä¸ŃåĽ½æ±½è½¦
    0.24
     Patriot
    0.24
     unfolds
    0.23
    Activations Density 5.339%

    No Known Activations