© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 503
    Prev
    Next
    INDEX
    Explanations

    say Tang dynasty

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

    No Comments

    Negative Logits
    阿根廷
    -27.75
    葡萄牙
    -23.50
    挪威
    -23.00
    意大利
    -22.63
    比利时
    -22.13
     Uruguay
    -21.63
    巴西
    -21.38
    Brazil
    -21.13
     Brazil
    -21.13
    阿根
    -20.88
    POSITIVE LOGITS
    大唐
    36.00
    长安
    35.25
    隋
    34.00
    西安市
    33.00
    唐朝
    32.75
    西安
    32.25
    唐代
    28.25
    浐
    28.13
    鄠
    27.88
     Baghdad
    27.63
    Activations Density 0.265%

    No Known Activations