© 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. 44849
    Prev
    Next
    INDEX
    Explanations

    Ville, CityVille, FarmVille

    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
    Not in Any Lists

    No Comments

    Negative Logits
    1
    -0.07
    该æĬĢæľ¯
    -0.06
     gar
    -0.06
     Ser
    -0.06
    -0.06
    0
    -0.06
    äºĨä¸ĢåĪĩ
    -0.06
    该åī§
    -0.06
     indis
    -0.06
    men
    -0.05
    POSITIVE LOGITS
    ãģ¨ãģĦãģ£ãģŁ
    0.14
    ãģĦãģļãĤĮ
    0.12
     alike
    0.11
     respectively
    0.11
    è¿Ļ两款
    0.11
    åIJĦèĩªçļĦ
    0.10
    ãģ¨ãĤĤãģ«
    0.10
    ãģĿãģĹãģ¦
    0.10
     ê·¸ë¦¬ê³ł
    0.10
    è¿Ļ两ç§į
    0.10
    Activations Density 0.180%

    No Known Activations