© 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. 2425
    Prev
    Next
    INDEX
    Explanations

    say "师"

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

    No Comments

    Negative Logits
    urga
    -17.63
    헬
    -16.25
     Races
    -15.81
     HEL
    -15.50
    .Annotation
    -15.13
     vé
    -14.81
    Vote
    -14.69
     PROP
    -14.50
     evacuation
    -14.06
     Contest
    -14.00
    POSITIVE LOGITS
    师
    90.50
    師
    74.00
     ser
    60.50
     Ser
    56.75
    Ser
    53.75
    -ser
    52.75
    ser
    52.00
    _ser
    51.00
    (serial
    48.75
    师兄
    47.00
    Activations Density 0.118%

    No Known Activations