© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 35073
    Prev
    Next
    INDEX
    Explanations

    looping through lists or sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    kau
    -0.07
    两项
    -0.07
    -validator
    -0.07
    ä¸¤äººåľ¨
    -0.07
    ä¸¤åĽ½
    -0.07
    ä¸ī人
    -0.07
    itzer
    -0.07
    etek
    -0.07
    è¿Ļ两ç§į
    -0.07
    jab
    -0.06
    POSITIVE LOGITS
    /*/
    0.08
    æŃ¤èµ·å½¼ä¼ı
    0.07
    .each
    0.07
    èĩªæµģ
    0.07
    znÄĽ
    0.07
     furn
    0.07
    æĺ¯æ¯ı个
    0.07
    èĩªç«ĭ
    0.07
    olatile
    0.07
     isl
    0.07
    Activations Density 0.106%

    No Known Activations