© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48633
    Prev
    Next
    INDEX
    Explanations

    excretion and collecting duct

    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
    èĬª
    -0.07
    åıªæĺ¯ä¸Ģç§į
    -0.07
    轻奢
    -0.06
     anne
    -0.06
    æ³Ľ
    -0.06
    kans
    -0.06
    hurst
    -0.06
     swo
    -0.06
     resize
    -0.06
     tighter
    -0.06
    POSITIVE LOGITS
    asics
    0.08
    GOR
    0.08
    è¾ĵåĩº
    0.08
    èĤ¾èĦı
    0.08
    åĽ°éļ¾çļĦ
    0.07
    æİĴåĩº
    0.07
    CHIP
    0.07
    awai
    0.07
    UDGE
    0.07
     episod
    0.07
    Activations Density 0.024%

    No Known Activations