© 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. 646
    Prev
    Next
    INDEX
    Explanations

    say Tibet

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

    No Comments

    Negative Logits
    漯
    -22.00
    是韩国
    -21.63
     Jacksonville
    -21.63
    玳
    -20.63
     Wilmington
    -20.50
    江门
    -20.25
     Purdue
    -20.13
    颍
    -19.88
    湛江
    -19.50
    阜阳
    -19.50
    POSITIVE LOGITS
    西藏
    57.25
     Tibetan
    56.50
     Tibet
    53.25
    拉萨
    51.50
    糌
    48.00
    青海
    45.50
    青海省
    44.75
    牦
    44.75
    高原
    43.00
    西宁
    40.00
    Activations Density 0.276%

    No Known Activations