© 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. 796
    Prev
    Next
    INDEX
    Explanations

    say grape

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

    No Comments

    Negative Logits
    宝安
    -24.38
    Iraq
    -24.38
    湖北
    -24.25
    安庆
    -24.25
     Kuwait
    -23.88
    Saudi
    -23.25
    湖北省
    -22.63
     Stamford
    -22.63
    东莞市
    -22.63
     Bahrain
    -22.13
    POSITIVE LOGITS
    葡萄
    52.50
    葡萄酒
    48.00
     grape
    42.75
     grapes
    42.50
     wine
    40.25
     vine
    39.25
     Bordeaux
    37.50
     Wine
    37.25
     Vine
    34.75
    葡
    34.25
    Activations Density 0.090%

    No Known Activations