© 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. 39324
    Prev
    Next
    INDEX
    Explanations

    text or words

    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
     prém
    -0.07
    nh
    -0.07
    pez
    -0.07
    ÑģÑĤин
    -0.07
    ç«ł
    -0.07
    ä¸İåIJ¦
    -0.07
     premature
    -0.07
     nihil
    -0.07
    innen
    -0.07
    åIJĦæī§
    -0.07
    POSITIVE LOGITS
    ลà¹īวà¸Ļ
    0.07
    èĢĮéĿŀ
    0.07
    åıĻè¿°
    0.07
    貨幣
    0.07
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    0.07
    igy
    0.07
    urado
    0.07
    izo
    0.07
     rather
    0.07
    æ¡£
    0.06
    Activations Density 0.008%

    No Known Activations