© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 633
    Prev
    Next
    INDEX
    Explanations

    Afghanistan

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

    No Comments

    Negative Logits
    在广州
    -34.25
    在深圳
    -33.75
    深圳市
    -32.75
    广州市
    -32.75
    广东省
    -32.50
    广州
    -32.25
    江门
    -31.75
    珠海
    -30.88
    深圳
    -30.13
    梅州
    -29.50
    POSITIVE LOGITS
     Afghan
    52.25
     Kabul
    52.00
    阿富汗
    48.50
     Afghanistan
    47.00
     Taliban
    43.75
     Uzbek
    34.75
     Nepal
    34.25
    Af
    31.38
     Pakistan
    30.75
     Pakistani
    30.38
    Activations Density 0.077%

    No Known Activations