© 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. 625
    Prev
    Next
    INDEX
    Explanations

    say "potato"

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

    No Comments

    Negative Logits
    梅州
    -25.00
    东莞市
    -24.75
    广东省
    -24.38
    广州市
    -23.75
    海湾
    -22.88
    浈
    -22.38
    厦门市
    -22.38
    汕
    -21.38
    汕头
    -21.00
    赣州
    -20.88
    POSITIVE LOGITS
     potato
    54.00
     Potato
    50.00
    土豆
    46.50
     potatoes
    43.50
    薯
    40.00
    红薯
    37.75
    🥔
    29.00
     tub
    28.00
    Pot
    25.88
    黄瓜
    25.38
    Activations Density 0.065%

    No Known Activations