© 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. 1915
    Prev
    Next
    INDEX
    Explanations

    [China] => [China]

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

    No Comments

    Negative Logits
     Chinese
    -50.25
     China
    -50.25
    China
    -48.25
    Chinese
    -45.75
    中国
    -43.50
    中国的
    -40.50
    -China
    -40.50
     china
    -40.00
     chinese
    -40.00
     중국
    -37.75
    POSITIVE LOGITS
    Vector
    16.00
    speaker
    15.69
     vector
    15.50
    珐
    15.06
    url
    15.06
     Electrical
    14.44
     ELECT
    14.44
    _motor
    14.31
    _IV
    14.25
     Vector
    14.19
    Activations Density 0.400%

    No Known Activations