© 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. 28478
    Prev
    Next
    INDEX
    Explanations

    running FreeBSD or Windows

    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
    æĽ´é«ĺçļĦ
    -0.07
    chine
    -0.07
    ä¸įéļ¾
    -0.07
    ASIL
    -0.07
    chet
    -0.07
    áŀŁáŁĭ
    -0.07
    ichter
    -0.07
    zeni
    -0.07
    aupt
    -0.06
    çļĦéĤ£äºĽ
    -0.06
    POSITIVE LOGITS
    ä½ķç§į
    0.09
     either
    0.08
    either
    0.08
     single
    0.08
    çļĦè¿ĺæĺ¯
    0.07
     berupa
    0.07
     _______,
    0.07
    éĿŀ
    0.07
     dạng
    0.07
     عبارة
    0.07
    Activations Density 0.067%

    No Known Activations