© 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. 3980
    Prev
    Next
    INDEX
    Explanations

    appropriate indentation

    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
    endor
    -0.08
    ajib
    -0.08
    ivière
    -0.07
    åħ«ä¹Ŀ
    -0.07
    oire
    -0.07
    ynu
    -0.07
    ambu
    -0.07
    ég
    -0.07
    å¿ĹæĪIJ
    -0.07
     wikit
    -0.07
    POSITIVE LOGITS
     \"
    0.08
    è¿ĺå°Ĩ
    0.07
    ä½łè¿ĺåı¯ä»¥
    0.07
    elleen
    0.07
     also
    0.07
     inoltre
    0.06
    è¿ĺä¼ļ
    0.06
    è¿ĺä¼ļåĩºçİ°
    0.06
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.06
     remaining
    0.06
    Activations Density 0.206%

    No Known Activations