© 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. 1830
    Prev
    Next
    INDEX
    Explanations

    Taiwan

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

    No Comments

    Negative Logits
    台湾
    -31.13
    台
    -29.38
     Taiwan
    -28.38
    臺
    -26.13
    /mac
    -25.63
     macro
    -24.75
     mac
    -24.75
    mac
    -24.00
     Taiwanese
    -23.88
    (mac
    -23.75
    POSITIVE LOGITS
    .paint
    16.13
     pdf
    16.13
     Golf
    15.44
     England
    15.38
     painter
    15.13
     vect
    15.13
     vector
    14.94
    psi
    14.94
     psychology
    14.81
     Painter
    14.81
    Activations Density 0.110%

    No Known Activations