© 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. 642
    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
     French
    -31.00
     France
    -29.50
    French
    -28.63
     franc
    -28.63
    France
    -28.50
    巴黎
    -27.88
    湘
    -27.63
    法国
    -27.25
    长沙市
    -27.13
    常德
    -27.13
    POSITIVE LOGITS
    汕头
    25.88
     Gdańsk
    25.13
     Gaza
    24.75
    南沙
    24.25
    榆林
    23.50
     الإمارات
    23.25
    烟台
    23.00
    东营
    22.88
    惠州
    21.88
    汕
    21.75
    Activations Density 0.452%

    No Known Activations