© 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. 758
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
    umul
    -0.07
    ç½ĹæĽ¼
    -0.07
    à¹ĥหà¹īà¸Ļ
    -0.07
    ulo
    -0.07
    locks
    -0.07
    ç¾ŀ涩
    -0.07
    çģ«çº¿
    -0.07
    Õ¡Õ¾
    -0.07
    _LINES
    -0.06
    è¾Ľè¾£
    -0.06
    POSITIVE LOGITS
    æ¯Ķèĩªå·±
    0.09
    æ¯Ķä»ĸ
    0.08
    uhi
    0.07
    ạ
    0.07
    ãģĵãģ¡ãĤīãĤĤ
    0.07
    åIJĮ为
    0.07
    sama
    0.07
    ä¸ºä½łæݨèįIJ
    0.06
    ionali
    0.06
    åı¯èĥ½åľ¨
    0.06
    Activations Density 0.170%

    No Known Activations