© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15001
    Prev
    Next
    INDEX
    Explanations

    say Chinese

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

    No Comments

    Negative Logits
    CRET
    -16.38
    dí
    -15.56
    гон
    -15.19
     persec
    -14.56
     eclipse
    -14.50
    ovie
    -14.31
    .getColor
    -14.31
    iples
    -14.25
    azy
    -13.75
     mxArray
    -13.69
    POSITIVE LOGITS
    China
    17.38
     China
    17.25
    Chinese
    16.50
     Chinese
    16.38
    城市
    16.25
    北方
    16.00
    Formats
    15.75
     Beijing
    15.25
    秦
    15.19
    城乡
    15.13
    Activations Density 0.116%

    No Known Activations