© 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. 1211
    Prev
    Next
    INDEX
    Explanations

    say 文献

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    茶园
    -16.75
     circuit
    -16.75
    湖北
    -16.13
     güneş
    -16.00
     turbine
    -15.63
     circuits
    -15.50
    Styles
    -15.38
    gba
    -15.31
    电路
    -15.31
    滟
    -15.19
    POSITIVE LOGITS
    语言
    24.13
     Book
    23.13
    book
    22.13
    Book
    22.00
    language
    21.25
    _book
    20.88
     DOCUMENT
    20.63
    书
    20.63
     book
    20.50
     language
    20.50
    Activations Density 0.283%

    No Known Activations