© 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. 41455
    Prev
    Next
    INDEX
    Explanations

    right side

    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
    æľīéģĵ
    -0.08
    ãĤīãģĭ
    -0.07
    äºĭæĥħ
    -0.07
    央
    -0.07
    æ½ĩæ´Ĵ
    -0.07
    ample
    -0.07
    ë°±
    -0.06
    ä¾ł
    -0.06
    ning
    -0.06
    åįķä½įåIJį称
    -0.06
    POSITIVE LOGITS
    è¿ĻæĦıåij³çĿĢ
    0.09
    ersch
    0.09
    æĦıåij³çĿĢ
    0.08
    æīĢ以对äºİ
    0.08
    æīĢ以å½ĵ
    0.07
    ssen
    0.07
    eschi
    0.07
    èĥĮæĻ¯ä¸ĭ
    0.07
    çݯå¢ĥä¸ĭ
    0.07
    æķħèĢĮ
    0.07
    Activations Density 0.038%

    No Known Activations