© 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. 18421
    Prev
    Next
    INDEX
    Explanations

    temperature and 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
    nö
    -0.07
    æķ°éĩıæľīéĻIJ
    -0.07
    ipse
    -0.06
    /lg
    -0.06
     propor
    -0.06
    æ¯Ķä¾ĭ为
    -0.06
    è¥¿åŁŁ
    -0.06
     propTypes
    -0.06
    å°ıå·§
    -0.06
    éĺ¿åį¡
    -0.06
    POSITIVE LOGITS
     temperatures
    0.10
     temperature
    0.10
     ambient
    0.10
    温度
    0.09
     conditions
    0.09
    çݯå¢ĥ温度
    0.09
    temperature
    0.09
    conditions
    0.09
    Conditions
    0.09
    温度åĴĮ
    0.08
    Activations Density 0.027%

    No Known Activations