© 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. 44557
    Prev
    Next
    INDEX
    Explanations

    code comments and programming contexts

    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
    ajat
    -0.07
    วà¹Īาà¸ģาร
    -0.07
    åı¦ä¸Ģ端
    -0.06
    åķĨä½ı
    -0.06
    绾ç»İ
    -0.06
    æĹłçIJĨ
    -0.06
    thing
    -0.06
    æĶ¾çļĦ
    -0.06
    amas
    -0.06
     wissen
    -0.06
    POSITIVE LOGITS
    Ñĸм
    0.08
    etlen
    0.07
    маÑģ
    0.07
    ÙĬاب
    0.07
     Neub
    0.07
    plom
    0.07
    NDER
    0.07
     provided
    0.07
     казал
    0.07
    Anime
    0.06
    Activations Density 0.013%

    No Known Activations