© 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. 32494
    Prev
    Next
    INDEX
    Explanations

    ports or medical terms

    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
    ä¸ĢæĹ¦è¢«
    -0.08
    ombe
    -0.07
     specie
    -0.07
    åŁĭ
    -0.07
    ä¸ĢæŦ
    -0.07
    çī©ç§į
    -0.07
    åĩºèµ°
    -0.07
    家åºŃåĴĮ
    -0.07
    ä¸Ģåıij
    -0.07
    timb
    -0.07
    POSITIVE LOGITS
    好åĿı
    0.08
    åħ·æľī丰å¯ĮçļĦ
    0.07
    çļĦ好åĿı
    0.07
     Kur
    0.07
    ä¸įæĸŃä¼ĺåĮĸ
    0.07
    ÙĪدة
    0.06
    ingerprint
    0.06
    à¸Ľà¸£à¸±à¸ļà¸Ľà¸£à¸¸à¸ĩ
    0.06
    ugar
    0.06
    zan
    0.06
    Activations Density 1.325%

    No Known Activations