© 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. 869
    Prev
    Next
    INDEX
    Explanations

    say "Japanese" words

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

    No Comments

    Negative Logits
    WhatsApp
    -21.50
    酸奶
    -19.88
    蜂蜜
    -19.25
     mascara
    -18.88
    VRT
    -18.88
    饽
    -17.88
    (rt
    -17.75
    FTA
    -17.63
    IPA
    -17.50
    (ft
    -17.25
    POSITIVE LOGITS
    日军
    34.25
     Japanese
    33.75
    Japanese
    31.50
     Taiwanese
    31.00
    抗战
    30.13
    重庆
    30.00
    日本
    29.75
     Shanghai
    29.63
     Taiwan
    29.38
     Jiang
    29.00
    Activations Density 0.261%

    No Known Activations