© 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. 1992
    Prev
    Next
    INDEX
    Explanations

    any => sugar

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

    No Comments

    Negative Logits
     sugar
    -39.50
    糖
    -37.00
    Sugar
    -36.00
     Sugar
    -34.75
     sugars
    -32.50
     сахар
    -28.88
     сах
    -28.25
    白糖
    -27.13
    糖果
    -23.13
    糖尿病
    -22.25
    POSITIVE LOGITS
     Palestine
    19.75
    ART
    18.38
     earth
    17.88
    arty
    16.88
    -earth
    16.75
     Philadelphia
    16.25
     Earth
    16.13
    art
    16.13
    -Israel
    16.00
    ARTH
    15.94
    Activations Density 0.097%

    No Known Activations