© 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. 3338
    Prev
    Next
    INDEX
    Explanations

    say "community"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    元素
    -21.63
     element
    -20.00
    [element
    -19.25
    element
    -19.13
     Element
    -19.00
    -elements
    -19.00
    (Element
    -18.75
    .Element
    -18.50
    -element
    -18.38
    Element
    -17.88
    POSITIVE LOGITS
    社区
    89.50
     community
    87.00
    Community
    79.50
    community
    78.50
     Community
    77.50
    社區
    69.50
     communities
    63.50
    _community
    63.00
    -community
    60.25
    .community
    60.25
    Activations Density 0.376%

    No Known Activations