© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17036
    Prev
    Next
    INDEX
    Explanations

    you're/you've/you can't

    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
    ä¸įåIJĮçļĦ人
    -0.08
     fascinated
    -0.08
    åĸľæ¬¢çļĦ
    -0.08
    çļĦåħ´è¶£
    -0.08
    æķħæĦıçļĦ
    -0.07
    åĵģ读
    -0.07
     interested
    -0.07
    -interest
    -0.07
    ä½łåĸľæ¬¢
    -0.07
    为åķ¥
    -0.07
    POSITIVE LOGITS
    å®ŀè·µç»ıéªĮ
    0.08
    æīĭå¿Ļ
    0.08
    è¯ķè¿ĩ
    0.08
    éĿ¢ä¸´çĿĢ
    0.08
    å®ŀéĻħæĵįä½ľ
    0.08
     tried
    0.07
    èĩªè´£
    0.07
    并已
    0.07
    æij¸ç´¢
    0.07
    è¯ķ
    0.07
    Activations Density 0.171%

    No Known Activations