© 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. 13694
    Prev
    Next
    INDEX
    Explanations

    ancient Greece, medieval disputation, magic circle

    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
    quera
    -0.07
    ç®Ģ书
    -0.07
    èij¬
    -0.07
    antt
    -0.07
    çļĦè¯Ŀ
    -0.06
    ophe
    -0.06
    踩
    -0.06
    à¹ĩà¸ĩ
    -0.06
    ank
    -0.06
    ement
    -0.06
    POSITIVE LOGITS
    Ùĩب
    0.08
    è¿Ļ便æĺ¯
    0.08
    laise
    0.07
    stown
    0.07
    vik
    0.07
    itics
    0.07
    äºijä¸Ń
    0.07
    оÑĢÑĤи
    0.07
    пл
    0.07
    ิริ
    0.07
    Activations Density 0.001%

    No Known Activations