© 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. 44358
    Prev
    Next
    INDEX
    Explanations

    medical, line, department, man, notification, tattoo, diver, comedies, blood

    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
    ä¸Ńåįİ人æ°ijåħ±åĴĮåĽ½åĪijæ³ķ
    -0.07
    elight
    -0.07
    ConfigurationException
    -0.07
    oyer
    -0.06
    \Configuration
    -0.06
     Bros
    -0.06
    ä»¬åľ¨
    -0.06
    INO
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    é±¼èĤī
    -0.06
    POSITIVE LOGITS
    åĴĮç¾İåĽ½
    0.11
    åĴĮæĹ¥æľ¬
    0.11
    åĴĮä¸ŃåĽ½
    0.10
    åĴĮä¸Ĭæµ·
    0.10
    ä¸İç¾İåĽ½
    0.09
    еме
    0.08
    ä¸İä¸ŃåĽ½
    0.08
    idios
    0.08
    åĴĮéĺ¿
    0.08
    neas
    0.08
    Activations Density 1.122%

    No Known Activations