© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18204
    Prev
    Next
    INDEX
    Explanations

    geographical/professional origins

    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
    åľ¨ä¸ĢæĹģ
    -0.08
    åľ¨æĹģè¾¹
    -0.07
    åľ¨åĨľæĿij
    -0.07
    å±ħä½ıåľ¨
    -0.07
    åĪĨå¸ĥåľ¨
    -0.07
    åľ¨åĮ»éĻ¢
    -0.07
    åľ¨æł¡åĽŃ
    -0.06
    åŃĺåľ¨äºİ
    -0.06
    æīĢåľ¨åįķä½į
    -0.06
    åŀĴ
    -0.06
    POSITIVE LOGITS
    åĴĮä¸Ĭæµ·
    0.15
    éĤ£éĩĮçļĦ
    0.15
    çŃīåľ°çļĦ
    0.12
    åĴĮæĹ¥æľ¬
    0.11
     AllÃŃ
    0.11
    åĴĮç¾İåĽ½
    0.11
    çŃīåľ°
    0.11
    åĴĮä¸ŃåĽ½
    0.10
    å½ĵåľ°çļĦ
    0.10
    ä¸Ĭ空
    0.10
    Activations Density 1.253%

    No Known Activations