© 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. 1147
    Prev
    Next
    INDEX
    Explanations

    Egypt

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

    No Comments

    Negative Logits
     Egypt
    -44.75
     Egyptian
    -44.25
    埃及
    -42.75
    Egypt
    -42.75
     Egyptians
    -40.75
    gypt
    -28.25
     Cairo
    -28.13
     المصري
    -27.75
     مصر
    -27.63
     المصرية
    -27.63
    POSITIVE LOGITS
    sound
    19.50
    声
    19.00
    Sound
    18.00
    海鲜
    17.63
     sound
    17.63
     JB
    16.75
    山东
    16.38
    打球
    16.25
     Marine
    15.88
     Sơn
    15.88
    Activations Density 0.131%

    No Known Activations