© 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. 33989
    Prev
    Next
    INDEX
    Explanations

    temperature transitions

    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
    æĢ»æķ°
    -0.08
    æ¯Ķä¾ĭ为
    -0.08
    æķ°éĩı为
    -0.08
    éĿ¢ç§¯ä¸º
    -0.08
    åĢįå¢ŀ
    -0.07
     Ratio
    -0.07
    çŃĿ
    -0.07
     ampl
    -0.07
    SourceType
    -0.07
    æ®´
    -0.07
    POSITIVE LOGITS
     temperatures
    0.11
    çĨĶçĤ¹
    0.10
    emperature
    0.09
    温度
    0.08
     temperature
    0.08
    temperature
    0.08
    çļĦ温度
    0.08
     ÑĤемпеÑĢаÑĤÑĥ
    0.08
     Fahrenheit
    0.08
     ÑĤемпеÑĢаÑĤÑĥÑĢа
    0.08
    Activations Density 0.018%

    No Known Activations