© 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. 1572
    Prev
    Next
    INDEX
    Explanations

    rice

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

    No Comments

    Negative Logits
     Rice
    -39.25
     rice
    -37.75
    rice
    -30.13
    稻
    -29.63
    水稻
    -24.88
    米饭
    -22.13
    秦
    -21.63
     Vietnamese
    -21.38
     gạo
    -21.00
    �
    -20.63
    POSITIVE LOGITS
    fst
    18.00
    カー
    17.25
    WND
    17.13
     authToken
    17.00
     windows
    17.00
    fter
    16.75
    -window
    16.25
    窗口
    16.13
     hWnd
    15.94
     Wolff
    15.94
    Activations Density 0.069%

    No Known Activations