© 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. 693
    Prev
    Next
    INDEX
    Explanations

    say Z words

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

    No Comments

    Negative Logits
    巴黎
    -30.88
    墨西哥
    -29.75
    法国
    -28.13
     Paris
    -27.88
     Marseille
    -27.50
    丹麦
    -27.25
     Danish
    -27.13
     French
    -26.00
    Paris
    -25.75
     France
    -25.38
    POSITIVE LOGITS
     Zimbabwe
    41.75
    浉
    26.88
     Rhodes
    26.88
    信阳
    26.38
     zb
    24.63
     Zh
    24.00
    ZH
    22.63
     Zambia
    22.38
     Mug
    22.25
    Zh
    22.25
    Activations Density 0.028%

    No Known Activations