© 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. 1538
    Prev
    Next
    INDEX
    Explanations

    [glucose] => [glucose]

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

    No Comments

    Negative Logits
     glucose
    -27.50
     sugar
    -26.50
    糖
    -26.13
    糖尿病
    -25.75
     diabetes
    -25.50
    血糖
    -24.25
     sugars
    -24.13
    葡萄
    -22.88
    白糖
    -22.50
     graph
    -21.63
    POSITIVE LOGITS
    arty
    19.13
    cart
    18.63
    art
    17.75
     cart
    17.25
    ART
    17.25
     Art
    15.94
    (cart
    15.94
     Artem
    15.38
    邢台
    15.19
     card
    15.13
    Activations Density 0.076%

    No Known Activations