© 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. 21824
    Prev
    Next
    INDEX
    Explanations

    edema and fluid retention

    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
    à¸Ħวัà¸Ļ
    -0.09
     cháy
    -0.08
    asers
    -0.08
    å®ĮæĪIJçİĩ
    -0.08
    çģ¿
    -0.08
    æĹłçĥŁ
    -0.08
    ลัย
    -0.08
    çĥ¨
    -0.08
    é«ĺæĸ°æĬĢæľ¯äº§ä¸ļå¼ĢåıijåĮº
    -0.08
    atitude
    -0.08
    POSITIVE LOGITS
     water
    0.09
    æ°´
    0.09
    æ°´åĪ©
    0.08
    æ³Ľæ»¥
    0.08
    æĺ¯æ°´
    0.08
    æ¶ĪèĤ¿
    0.08
    water
    0.08
     Water
    0.08
     hypert
    0.08
    æ°´èĤ¿
    0.08
    Activations Density 0.062%

    No Known Activations