© 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. 1887
    Prev
    Next
    INDEX
    Explanations

    ultraviolet

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

    No Comments

    Negative Logits
    紫外线
    -25.63
     UV
    -23.00
    紫外
    -22.88
     ultr
    -21.25
    SCRIPT
    -20.75
     CSS
    -20.63
    CSS
    -20.50
    UV
    -20.00
    纱
    -19.50
     Scripts
    -19.25
    POSITIVE LOGITS
    ByEmail
    17.25
     Engine
    17.25
    工程
    17.25
    ущ
    17.00
     engineering
    17.00
    /engine
    16.88
     Engineers
    16.38
    engine
    16.38
    ENGINE
    16.38
     engineers
    16.25
    Activations Density 0.086%

    No Known Activations