© 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. 2618
    Prev
    Next
    INDEX
    Explanations

    say "监管"

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

    No Comments

    Negative Logits
    文明
    -17.13
    mill
    -15.88
    .tv
    -15.56
     MILL
    -15.38
    rev
    -15.25
    (prop
    -14.88
     Mé
    -14.88
    tml
    -14.88
     Mill
    -14.81
     meth
    -14.81
    POSITIVE LOGITS
     Reg
    71.50
    Reg
    70.50
     reg
    69.00
    reg
    64.50
    监管
    62.75
    	reg
    60.25
    (reg
    59.00
    _reg
    58.75
     REG
    58.00
    -reg
    57.50
    Activations Density 0.091%

    No Known Activations