© 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. 741
    Prev
    Next
    INDEX
    Explanations

    say "biblical names"

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

    No Comments

    Negative Logits
    匈
    -25.38
     Cairo
    -25.13
    上海
    -24.75
    埃及
    -24.13
    在上海
    -23.50
    浦东
    -23.50
     Munich
    -23.00
    上海市
    -22.88
    宁夏
    -22.88
     Lahore
    -22.63
    POSITIVE LOGITS
     Saul
    25.00
    大豆
    22.75
    泰安
    21.13
     Samuel
    19.00
     David
    18.13
     DAO
    17.50
    大卫
    17.25
     dao
    17.00
     df
    16.25
    David
    16.25
    Activations Density 0.111%

    No Known Activations