© 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. 58626
    Prev
    Next
    INDEX
    Explanations

    low-level vision

    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
    Readable
    -0.08
    èļĢ
    -0.07
    åĴĮä¸įèī¯
    -0.07
    çļĦ人æĸĩ
    -0.07
    Ñģал
    -0.07
    enges
    -0.07
    ä¸įæ¼ı
    -0.07
    çļĦ人éĻħ
    -0.07
    ä¸įçķĻ
    -0.06
    iqu
    -0.06
    POSITIVE LOGITS
    cule
    0.07
     silent
    0.07
    armacy
    0.07
     Silent
    0.07
    akta
    0.07
    æ²īé»ĺ
    0.07
    åºŃ
    0.07
    鬼ç¥ŀ
    0.07
    à¹Ģà¸ĩียà¸ļ
    0.07
    refix
    0.07
    Activations Density 0.342%

    No Known Activations