© 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. 12449
    Prev
    Next
    INDEX
    Explanations

    degrees Celsius or Fahrenheit

    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
    åIJįæĢĿ
    -0.10
    ansom
    -0.10
    λÎŃ
    -0.09
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.08
    èįŁ
    -0.08
     membel
    -0.08
    æĮģä¹ĭ以
    -0.08
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    -0.08
    人ä¸Ģ
    -0.08
    Äija
    -0.08
    POSITIVE LOGITS
     Celsius
    0.12
     temperatures
    0.12
    温度计
    0.11
     Fahrenheit
    0.11
     temperature
    0.11
    温差
    0.11
    温度
    0.11
     thermometer
    0.11
     Temperature
    0.10
    æijĦæ°ı
    0.10
    Activations Density 0.005%

    No Known Activations