© 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. 58989
    Prev
    Next
    INDEX
    Explanations

    Chinese or Japanese names/words

    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
    <|box_end|>
    -0.08
    ize
    -0.08
    е
    -0.07
    å¿ĺè¿Ķ
    -0.07
    weiler
    -0.07
    åĴĮ帮åĬ©
    -0.07
    ами
    -0.07
    Ùİاع
    -0.07
    æ»¡çľ¼
    -0.07
    scribe
    -0.07
    POSITIVE LOGITS
    o
    0.11
    न
    0.10
    èĩªå·±
    0.10
    bsites
    0.10
    ed
    0.09
    ãĥ³
    0.09
    ìį¨
    0.08
    ×ķ
    0.08
    Õ¶
    0.08
    à¹Ģà¸Ĺà¹īา
    0.07
    Activations Density 0.006%

    No Known Activations