© 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. 27776
    Prev
    Next
    INDEX
    Explanations

    sequence questions with numbers

    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
    ebro
    -0.07
    ÑħодиÑĤе
    -0.07
     paris
    -0.06
    ypy
    -0.06
    æ¨Ł
    -0.06
    ÑĤÑģÑı
    -0.06
    æŁ³
    -0.06
    踵
    -0.06
    Ñħода
    -0.06
    士æŀĹ
    -0.06
    POSITIVE LOGITS
    clearfix
    0.08
    书åŁİ
    0.08
     декла
    0.07
    ä¹Ŀ游
    0.07
    æĿ¡æĿ¡
    0.07
     пÑĢиви
    0.07
     заблÑĥ
    0.07
    å°½èģĮ尽责
    0.07
    riet
    0.07
    zyman
    0.07
    Activations Density 0.019%

    No Known Activations