© 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. 55643
    Prev
    Next
    INDEX
    Explanations

    abbreviations ending in parenthesis

    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
    باب
    -0.07
    å®ŀéĻħåĩºåıij
    -0.07
    èĩªæĭħ
    -0.06
     Dress
    -0.06
    bland
    -0.06
    çļĦ人äºĨ
    -0.06
    è¾ĥéķ¿çļĦ
    -0.06
    udo
    -0.06
    à®Łà®¿à®¯
    -0.06
    RTC
    -0.06
    POSITIVE LOGITS
     Sofort
    0.08
    notation
    0.07
    argon
    0.07
    ones
    0.07
    尼奥
    0.07
    骡
    0.07
     Corso
    0.07
    ench
    0.07
    asso
    0.07
    (dot
    0.06
    Activations Density 0.379%

    No Known Activations