© 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. 29857
    Prev
    Next
    INDEX
    Explanations

    Lady Gaga

    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
    bins
    -0.08
    ukan
    -0.07
     porod
    -0.07
    ä»İçİ°åľ¨å¼Ģå§ĭ
    -0.07
    bij
    -0.07
    عÛĮ
    -0.07
    à¹īà¸Ńà¸Ļ
    -0.06
    itional
    -0.06
    νομ
    -0.06
    å¼Ģå§ĭçļĦ
    -0.06
    POSITIVE LOGITS
    æī¬
    0.07
    ìķĪìĿ´
    0.07
    endt
    0.06
    æ·®
    0.06
    æ²IJ
    0.06
    ç«Ł
    0.06
    idado
    0.06
    大浪
    0.06
    æ»ļ
    0.06
    æıļ
    0.06
    Activations Density 0.010%

    No Known Activations