© 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. 1835
    Prev
    Next
    INDEX
    Explanations

    do not say alcohol

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

    No Comments

    Negative Logits
    酒
    -65.00
     alcohol
    -52.25
    饮酒
    -49.75
    喝酒
    -48.50
     Alcohol
    -47.50
    酒精
    -46.00
     wine
    -41.00
    酒业
    -38.50
     Wine
    -37.25
     alcoholic
    -37.25
    POSITIVE LOGITS
    肿瘤
    17.88
    Plot
    17.75
     Plot
    16.00
    螯
    15.88
    UBL
    15.81
    (te
    15.69
    dynamic
    15.69
     plotting
    15.31
     plot
    15.00
    _SL
    14.94
    Activations Density 0.043%

    No Known Activations