© 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. 29209
    Prev
    Next
    INDEX
    Explanations

    temperature measurement

    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
    æ¯Ķä¾ĭ为
    -0.09
    æ¯Ķä¾ĭçļĦ
    -0.07
    ukes
    -0.07
    æ¯Ķä¾ĭ
    -0.07
    è¶Ĭéķ¿
    -0.07
    æĢ»éĿ¢ç§¯
    -0.07
    usize
    -0.07
    иÑĤелÑĮÑģÑĤво
    -0.07
    åł°
    -0.07
    é«ĺ产
    -0.07
    POSITIVE LOGITS
     temperatures
    0.17
     temperature
    0.17
    温度
    0.16
     Celsius
    0.15
    temperature
    0.15
    çļĦ温度
    0.15
     Fahrenheit
    0.14
    Temperature
    0.14
     Temperature
    0.14
    温度çļĦ
    0.14
    Activations Density 0.104%

    No Known Activations