© 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. 3202
    Prev
    Next
    INDEX
    Explanations

    say Context

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    形
    -19.75
     array
    -17.63
     shape
    -17.25
    line
    -16.88
     line
    -16.75
     organisation
    -15.88
    形态
    -15.69
    property
    -15.38
     SetProperty
    -15.25
    人
    -15.13
    POSITIVE LOGITS
    Community
    21.88
    社区
    19.25
     Community
    19.13
    模块
    18.63
    Context
    18.63
    社區
    16.88
     community
    16.88
    eming
    16.50
    _context
    16.38
    context
    16.13
    Activations Density 0.004%

    No Known Activations