© 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. 39421
    Prev
    Next
    INDEX
    Explanations

    medical conditions and scientific 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
    Ñĭл
    -0.07
    åıijæĮ¥èĩªå·±çļĦ
    -0.07
    azon
    -0.07
    顺åºĶ
    -0.07
    毡
    -0.07
     ÙĪÙħÙĨÙĩا
    -0.07
    ì¼Ģ
    -0.07
    prise
    -0.07
    æĪŁ
    -0.07
    顺
    -0.06
    POSITIVE LOGITS
    artal
    0.08
    uda
    0.08
     legg
    0.08
    ä¸īé«ĺ
    0.07
    .Loader
    0.06
    深信
    0.06
    OfFile
    0.06
    udit
    0.06
    åĮĹä¸Ĭ
    0.06
    çĥŁ
    0.06
    Activations Density 0.173%

    No Known Activations