© 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. 60284
    Prev
    Next
    INDEX
    Explanations

    kings and emperors with roman numerals

    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
    ÃŃv
    -0.09
    ä»ķ
    -0.08
    åī¯éĥ¨éķ¿
    -0.08
    深港
    -0.08
     Séné
    -0.07
    raul
    -0.07
    妥
    -0.07
    åŃIJãģĮ
    -0.07
    丽èİİ
    -0.07
    ä¹ĭ士
    -0.07
    POSITIVE LOGITS
    åį³ä½į
    0.09
    éĻĽä¸ĭ
    0.08
    çĻ»åŁº
    0.08
     reigning
    0.08
    arella
    0.07
    à¸Ĺรà¸ĩ
    0.07
    æĩ¦å¼±
    0.07
     ruling
    0.07
     пÑĢеÑģÑĤ
    0.07
     pop
    0.07
    Activations Density 0.111%

    No Known Activations