© 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. 13843
    Prev
    Next
    INDEX
    Explanations

    php code

    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
    æĹłä»¥
    -0.08
    让æķ´ä¸ª
    -0.08
    anceled
    -0.08
    éķ¿æĮīè¯ĨåĪ«
    -0.07
    ceso
    -0.07
    adini
    -0.07
    Dettagli
    -0.07
    ÙĦز
    -0.07
    cancelled
    -0.07
    namespace
    -0.07
    POSITIVE LOGITS
     Args
    0.07
    èĢĥèĻij
    0.07
    æķ
    0.07
    umd
    0.07
    ase
    0.06
    ниÑģ
    0.06
    äºijå³°
    0.06
    äºĮåĪĨ
    0.06
    bid
    0.06
    RU
    0.06
    Activations Density 0.013%

    No Known Activations