© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1183
    Prev
    Next
    INDEX
    Explanations

    [开关] => [开关]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Switch
    -45.25
     switch
    -45.25
    Switch
    -45.00
     switches
    -44.00
    switch
    -43.75
     SWITCH
    -42.50
    开关
    -42.00
     switching
    -39.25
    -switch
    -38.00
     switched
    -37.75
    POSITIVE LOGITS
     Kod
    17.88
    ën
    15.81
     bó
    15.31
    炭
    15.00
    пон
    14.88
     poetic
    14.75
    诗意
    14.69
    ibil
    14.44
    诗
    14.31
     Hond
    14.25
    Activations Density 0.052%

    No Known Activations