© 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. 3259
    Prev
    Next
    INDEX
    Explanations

    say 族

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    -company
    -16.50
     companies
    -16.00
    行
    -15.94
    逸
    -15.56
     line
    -15.44
    模型
    -15.38
     treatment
    -15.38
    companies
    -14.94
     Companies
    -14.88
     treatments
    -14.81
    POSITIVE LOGITS
    族
    36.00
     family
    32.25
    家族
    29.00
    family
    27.63
     type
    26.13
    型
    26.13
    Family
    25.63
    _family
    25.38
     Family
    25.25
     FAMILY
    23.25
    Activations Density 0.055%

    No Known Activations