© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1709
    Prev
    Next
    INDEX
    Explanations

    [weather] => [weathering]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weather
    -55.25
    weather
    -51.25
    Weather
    -49.50
     Weather
    -49.00
    天气
    -48.75
    _weather
    -36.50
    /weather
    -35.75
    (weather
    -35.50
    气象
    -30.38
    .weather
    -29.63
    POSITIVE LOGITS
    技术创新
    16.50
    ulton
    16.13
     Spartan
    15.94
    渌
    15.75
    印花
    15.69
    파
    15.50
     column
    15.50
    -Israel
    15.38
    鲟
    15.31
    scriptId
    15.00
    Activations Density 0.055%

    No Known Activations