© 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. 63619
    Prev
    Next
    INDEX
    Explanations

    numbers in citations

    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
    åѦéĻ¢
    -0.07
    ä½£
    -0.06
    keiten
    -0.06
    åįļ大精深
    -0.06
    SearchParams
    -0.06
    æ¦Ĩ
    -0.06
     заÑģед
    -0.06
    ä¸Ĭåı¤
    -0.06
    æĪijè¡Į
    -0.06
    èĢĮä¸Ķè¿ĺæĺ¯
    -0.06
    POSITIVE LOGITS
    ä½ĻåĬĽ
    0.08
    管çIJĨç±»
    0.07
    noz
    0.07
    èĬĤåIJİ
    0.07
    zim
    0.07
    æĹłåıĮ
    0.07
    æ®ĩ
    0.07
     zob
    0.07
    ctal
    0.07
    æĹłåıį
    0.07
    Activations Density 0.008%

    No Known Activations