© 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. 45854
    Prev
    Next
    INDEX
    Explanations

    pick out or choose from

    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
     Dude
    -0.08
    çļĦ大éĩı
    -0.08
    é¼İé¼İ
    -0.07
    å·²ä¹ħ
    -0.07
    缸åħ³æ³ķå¾ĭ责任
    -0.07
     genug
    -0.07
    aced
    -0.07
    olato
    -0.07
    geg
    -0.07
    åįĩåĪĿ
    -0.06
    POSITIVE LOGITS
    åħ¶ä¸Ń
    0.10
     where
    0.08
    æŃ£ç¡®çļĦ
    0.08
    æŃ£ç¡®
    0.07
     correct
    0.07
    æŃ£ç¢ºçļĦ
    0.07
    åĶ¯ä¸Ģ
    0.07
    代表
    0.07
    åIJĪéĢĤçļĦ
    0.07
    羣æŃ£
    0.07
    Activations Density 0.008%

    No Known Activations