© 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. 1431
    Prev
    Next
    INDEX
    Explanations

    say "China"

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

    No Comments

    Negative Logits
    menus
    -15.25
     menus
    -14.13
    /log
    -13.94
     Logan
    -13.88
    oice
    -13.63
    (log
    -13.50
    Browse
    -13.31
    Slf
    -13.25
    /Card
    -13.25
    動物
    -13.19
    POSITIVE LOGITS
    中国的
    20.25
    -China
    19.50
     China
    18.38
    中国制造
    18.38
     chinese
    18.13
    中国
    18.13
    China
    17.75
     Chinese
    17.75
    对中国
    17.63
     china
    17.38
    Activations Density 0.142%

    No Known Activations