© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1111
    Prev
    Next
    INDEX
    Explanations

    [style] => [style]

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

    No Comments

    Negative Logits
     style
    -48.00
     styles
    -46.75
    风格
    -45.25
     Style
    -44.75
    	style
    -43.50
    Style
    -42.00
    style
    -41.00
     Styles
    -40.25
     STYLE
    -39.25
    _style
    -37.75
    POSITIVE LOGITS
    数学
    19.38
    Math
    18.38
     Math
    17.63
     mathematic
    17.63
    gal
    17.13
     mathematics
    16.63
     Mathematics
    16.50
    .compute
    16.00
    math
    15.81
    digital
    15.25
    Activations Density 0.105%

    No Known Activations