© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16155
    Prev
    Next
    INDEX
    Explanations

    say "unite"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    迟到
    -17.88
    翅膀
    -17.75
    辜
    -15.38
    黑客
    -15.38
    歪
    -15.00
    爪
    -14.94
     INSTALL
    -14.88
    翅
    -14.75
    qw
    -14.63
     Advisor
    -14.56
    POSITIVE LOGITS
    统一
    34.00
     unified
    33.00
     unify
    31.13
     unite
    30.63
     unity
    30.00
     Unified
    28.63
    整合
    28.63
     uniform
    28.63
    聚合
    27.88
     unit
    27.13
    Activations Density 0.793%

    No Known Activations