© 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. 3271
    Prev
    Next
    INDEX
    Explanations

    子

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     method
    -18.75
     Method
    -18.75
    method
    -18.63
    _method
    -18.25
    Method
    -18.25
    -method
    -17.75
    方法
    -17.38
     метод
    -16.38
    METHOD
    -16.38
     form
    -16.13
    POSITIVE LOGITS
    子
    61.00
     subset
    37.25
    ⼦
    34.25
    儿子
    32.25
     Subset
    32.25
    subset
    32.00
    子里
    31.25
    _subset
    29.63
    子公司
    29.50
     subsets
    29.38
    Activations Density 0.146%

    No Known Activations