© 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. 438
    Prev
    Next
    INDEX
    Explanations

    say place names

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

    No Comments

    Negative Logits
    (gp
    -16.25
    ⾦
    -15.69
    ⽩
    -13.88
    不可思
    -13.31
    tps
    -13.31
    (([
    -13.19
    襁
    -12.88
    叟
    -12.81
     рест
    -12.81
     Jo
    -12.69
    POSITIVE LOGITS
     Pakistan
    42.25
    无锡
    42.25
     Lahore
    42.25
    贵州
    42.00
     Bangladesh
    42.00
    巴基斯坦
    42.00
     Pakistani
    41.50
     Nepal
    41.50
    伊朗
    41.00
    银川
    41.00
    Activations Density 1.683%

    No Known Activations