© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 26138
    Prev
    Next
    INDEX
    Explanations

    thermal physics and decay

    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
     dese
    -0.06
    æĶ¿åºľä¿¡æģ¯åħ¬å¼Ģ
    -0.06
     Planta
    -0.06
    è¾ĥçŁŃ
    -0.06
    æĸĮ
    -0.06
    åīῬ¾
    -0.06
    жай
    -0.06
    à¹ģà¸Ľ
    -0.06
     desk
    -0.06
    å¼Ģå±ķç»ıèIJ¥æ´»åĬ¨
    -0.06
    POSITIVE LOGITS
    èĿĮ
    0.08
     thermal
    0.08
     baths
    0.08
    arton
    0.08
     позд
    0.08
    Late
    0.07
    .breakpoints
    0.07
    åŃĺæ´»
    0.07
     Late
    0.07
     census
    0.07
    Activations Density 0.011%

    No Known Activations