© 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. 2111
    Prev
    Next
    INDEX
    Explanations

    say "文明"

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

    No Comments

    Negative Logits
     reg
    -20.63
    	reg
    -19.00
     Reg
    -17.88
     Regents
    -17.88
     regs
    -17.25
    .Reg
    -16.25
    (reg
    -15.81
    _Reg
    -15.69
     Regression
    -15.63
    _Tab
    -15.56
    POSITIVE LOGITS
    文明
    57.25
     civilization
    38.75
    Civil
    37.00
    civil
    36.75
     civil
    36.50
     Civil
    35.50
     Eth
    34.25
    乙
    33.25
    eth
    32.75
    Eth
    31.13
    Activations Density 0.139%

    No Known Activations