© 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. 44568
    Prev
    Next
    INDEX
    Explanations

    plan, procedures, implement, documentation

    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
    cott
    -0.08
    æıIJæIJº
    -0.07
    ä¸ĵ家æĮĩåĩº
    -0.07
    çĶ±ä¸ŃåĽ½
    -0.07
    _compile
    -0.07
    åĴĮç¾İåĽ½
    -0.07
     laga
    -0.07
    æīĭæı¡
    -0.07
    ç»ıèIJ¥æ¨¡å¼ı
    -0.06
    InstanceOf
    -0.06
    POSITIVE LOGITS
    ä¸İ管çIJĨ
    0.08
    åħ¨åijĺ
    0.08
     budget
    0.07
    æ¸ħåįķ
    0.07
     SharePoint
    0.07
    enders
    0.07
    å°Ĩè¦ģ
    0.07
    forecast
    0.07
    è¯Ħä¼°
    0.07
    çĢijå¸ĥ
    0.07
    Activations Density 0.009%

    No Known Activations