© 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. 2513
    Prev
    Next
    INDEX
    Explanations

    say "业绩"

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

    No Comments

    Negative Logits
    	lib
    -16.63
    eka
    -15.50
    -den
    -15.31
    (power
    -15.19
    olia
    -15.19
    .rad
    -15.00
     Conduct
    -14.75
    规则
    -14.63
    roll
    -14.56
    avel
    -14.25
    POSITIVE LOGITS
    业绩
    51.25
    _perf
    33.25
     performance
    31.38
    perf
    30.38
    Performance
    29.38
     perf
    29.00
     PERFORMANCE
    28.63
    性能
    28.13
    绩
    28.13
    performance
    27.50
    Activations Density 0.028%

    No Known Activations