© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2318
    Prev
    Next
    INDEX
    Explanations

    weather and climate phenomena

    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·±éĻ·
    -0.08
     dáºŃp
    -0.08
    ิà¹Īม
    -0.07
     Habana
    -0.07
    åīįåĪĹ
    -0.07
     agil
    -0.07
     Samurai
    -0.07
    骨èĤī
    -0.07
    vene
    -0.07
    ÙĤت
    -0.07
    POSITIVE LOGITS
     weather
    0.13
     climate
    0.12
    天æ°Ķ
    0.11
    èĩªçĦ¶çݯå¢ĥ
    0.11
    /weather
    0.11
     temperature
    0.11
     conditions
    0.11
    weather
    0.10
    åıĺå¹»
    0.10
     clim
    0.10
    Activations Density 0.166%

    No Known Activations