© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 922
    Prev
    Next
    INDEX
    Explanations

    say "Buddhist"

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

    No Comments

    Negative Logits
    阿根廷
    -28.88
    西班牙
    -22.38
    Argentina
    -20.63
    潍
    -20.50
    梅西
    -20.25
    克里斯
    -20.25
    潍坊
    -20.13
     Uruguay
    -20.13
     Paolo
    -20.00
     Argentina
    -19.38
    POSITIVE LOGITS
     Buddhist
    52.50
     Buddhism
    49.25
     Buddha
    49.00
    佛教
    48.00
     Buddh
    46.50
    佛陀
    45.25
    佛法
    45.25
    禅
    41.75
    僧
    37.75
    印度
    37.50
    Activations Density 0.785%

    No Known Activations