© 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. 49338
    Prev
    Next
    INDEX
    Explanations

    temperature and physiological conditions

    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
    æľĿ天
    -0.09
    家ä½ı
    -0.09
    uret
    -0.08
    èĭ¦ç»ĥ
    -0.08
    å¤ļå°ij次
    -0.08
    è¸ıè¸ıå®ŀ
    -0.08
     fastest
    -0.07
     tapered
    -0.07
    FIN
    -0.07
    èĢį
    -0.07
    POSITIVE LOGITS
    çĩ
    0.07
    endale
    0.07
    clam
    0.07
     Dew
    0.06
    ITE
    0.06
    çİ®
    0.06
    oom
    0.06
    ite
    0.06
    oyer
    0.06
    çļĦç»ıèIJ¥
    0.06
    Activations Density 0.002%

    No Known Activations