© 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. 34429
    Prev
    Next
    INDEX
    Explanations

    medical treatments and compounds

    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
    kunde
    -0.07
    häl
    -0.06
    ignon
    -0.06
    æıIJåīį
    -0.06
    angsa
    -0.06
    èĩ¼
    -0.06
     variations
    -0.06
    篤
    -0.06
    ìŀIJ리
    -0.06
    åĴĮ客æĪ·
    -0.06
    POSITIVE LOGITS
    并举
    0.08
    åĴĮæĶ¹åĸĦ
    0.08
    ores
    0.08
    ç±»åĴĮ
    0.08
    åĴĮæĶ¯æĮģ
    0.08
    æľ¬é¡µ
    0.08
    /assert
    0.08
    åĬĽå¼º
    0.08
    èĢĮä¸į
    0.08
    ç±»çļĦ
    0.07
    Activations Density 0.004%

    No Known Activations