© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15806
    Prev
    Next
    INDEX
    Explanations

    say sugar

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

    No Comments

    Negative Logits
    铠
    -18.13
    ทหาร
    -17.25
     PCIe
    -17.25
     XML
    -17.00
     Capcom
    -16.63
    军事
    -16.38
    装甲
    -16.00
     xml
    -16.00
    /xml
    -15.88
     Military
    -15.75
    POSITIVE LOGITS
    糖
    44.50
     sugar
    43.75
     сахар
    41.00
     Sugar
    40.50
     sugars
    40.25
    Sugar
    38.75
    白糖
    38.75
     sweetness
    38.00
    甜
    38.00
     cache
    37.50
    Activations Density 0.210%

    No Known Activations