© 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. 2284
    Prev
    Next
    INDEX
    Explanations

    say "击"

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

    No Comments

    Negative Logits
    den
    -22.00
     Sem
    -21.38
     sem
    -20.38
    范
    -20.38
     Den
    -20.38
    _sem
    -20.00
    Sem
    -19.63
     param
    -19.25
    sem
    -18.88
    (param
    -18.75
    POSITIVE LOGITS
    击
    48.25
     strike
    39.75
     strikes
    36.00
     struck
    36.00
    擊
    35.25
    Strike
    33.00
     Strike
    31.00
    _strike
    30.88
    strike
    30.88
     striking
    27.38
    Activations Density 0.070%

    No Known Activations