© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 705
    Prev
    Next
    INDEX
    Explanations

    Mughal empire

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

    No Comments

    Negative Logits
    埃及
    -26.50
    深圳市
    -24.63
     Egyptian
    -23.88
    信阳
    -23.63
    椰
    -23.50
    Israeli
    -23.25
     Israeli
    -23.00
     Israelis
    -23.00
    Egypt
    -22.88
     Egyptians
    -22.63
    POSITIVE LOGITS
    白银
    16.75
    rs
    16.75
    寇
    16.75
     CST
    16.63
    cs
    16.13
    陕西
    15.88
    金银
    15.81
    azu
    15.63
    CS
    15.13
    (cs
    15.06
    Activations Density 0.138%

    No Known Activations