© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1241
    Prev
    Next
    INDEX
    Explanations

    wine => wine

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

    No Comments

    Negative Logits
     wine
    -48.75
    酒
    -46.50
     Wine
    -45.75
    葡萄酒
    -41.75
    wine
    -39.25
     wines
    -38.25
    红酒
    -35.50
    ワイン
    -31.88
    喝酒
    -30.25
    酒业
    -29.88
    POSITIVE LOGITS
    动态
    18.00
     Dynam
    17.88
     dynamic
    17.75
     Dynamic
    17.50
    dynamic
    17.25
    Dynamic
    16.38
    akk
    15.75
     dynamically
    15.50
     Arabs
    14.94
     dynam
    14.81
    Activations Density 0.057%

    No Known Activations