© 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. 1514
    Prev
    Next
    INDEX
    Explanations

    Asia

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

    No Comments

    Negative Logits
     Asians
    -35.25
     Asia
    -35.00
     Asian
    -35.00
    Asian
    -33.75
    亚洲
    -32.25
    Asia
    -32.00
    アジア
    -28.63
     asian
    -26.75
    亚太
    -25.75
     asia
    -25.63
    POSITIVE LOGITS
     vector
    17.50
     vectors
    17.25
     vect
    17.13
    еч
    17.00
    vector
    16.50
     VECTOR
    15.81
    数字化
    15.56
    葡萄牙
    15.31
     Magnetic
    15.31
    .code
    15.25
    Activations Density 0.085%

    No Known Activations