© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14077
    Prev
    Next
    INDEX
    Explanations

    say "Hindu" terms

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

    No Comments

    Negative Logits
    鸡肉
    -22.25
    权重
    -20.63
    博弈
    -20.50
     Costco
    -20.13
    像素
    -19.75
    镜头
    -19.50
    风险管理
    -19.50
    _mouse
    -19.50
    红酒
    -19.50
    _Mouse
    -19.38
    POSITIVE LOGITS
     Uttar
    17.75
     Utt
    17.38
     Sri
    17.13
     Sah
    16.75
     Ved
    16.50
     Kerala
    16.38
     Va
    16.13
     sut
    15.88
     lakh
    15.75
     Hindus
    15.38
    Activations Density 0.583%

    No Known Activations