© 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. 1932
    Prev
    Next
    INDEX
    Explanations

    drink => drink

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

    No Comments

    Negative Logits
     drink
    -40.75
     Drink
    -35.25
    drink
    -34.00
    饮
    -33.25
     drinks
    -33.25
     drinking
    -32.25
    Drink
    -30.63
     Drinking
    -30.50
    喝
    -29.63
    饮品
    -29.50
    POSITIVE LOGITS
    _EDITOR
    17.63
     Eigen
    17.25
    macro
    15.56
    棋
    15.25
    MAC
    15.00
    臺
    14.88
     macro
    14.75
    ellij
    14.69
    _CAR
    14.63
     edible
    14.38
    Activations Density 0.095%

    No Known Activations