© 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. 22740
    Prev
    Next
    INDEX
    Explanations

    "fever" disease

    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
    anei
    -0.08
    olling
    -0.08
    ölt
    -0.08
    èij©
    -0.08
    们çļĦ
    -0.07
    ima
    -0.07
    wers
    -0.07
    们
    -0.07
    chap
    -0.07
    们对
    -0.07
    POSITIVE LOGITS
    ä¼łåħ¥
    0.07
    æĿĨèıĮ
    0.07
    å¹¿æ³Ľå®£ä¼ł
    0.07
    -related
    0.07
    chnet
    0.07
    entan
    0.07
    kasse
    0.07
    सार
    0.06
     gang
    0.06
     lesser
    0.06
    Activations Density 0.096%

    No Known Activations