© 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. 651
    Prev
    Next
    INDEX
    Explanations

    say Azerbaijan

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

    No Comments

    Negative Logits
    岳阳
    -25.88
    信阳
    -25.25
    武汉市
    -25.13
    九江
    -24.75
     Dublin
    -23.50
    -Israel
    -23.38
    武汉
    -23.00
    埃及
    -22.63
     Rabbi
    -22.50
    南昌
    -22.50
    POSITIVE LOGITS
     Azerbai
    25.38
     Azerbaijan
    24.00
    GC
    20.63
     Caucas
    20.25
    陇
    19.75
     GC
    19.13
    zerbai
    19.00
     Taj
    18.25
     Guth
    18.13
     CJ
    18.00
    Activations Density 0.080%

    No Known Activations