© 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. 3319
    Prev
    Next
    INDEX
    Explanations

    say dash

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    公司的
    -23.38
    company
    -22.75
     company
    -22.13
     application
    -21.50
    -company
    -21.38
    公司
    -20.88
    connection
    -20.88
     connection
    -19.75
     COMPANY
    -19.50
    application
    -19.25
    POSITIVE LOGITS
     Side
    21.50
    Side
    20.75
     side
    20.13
    (side
    20.00
    侧
    19.13
    .side
    18.25
    _side
    17.75
    側
    16.88
     date
    16.88
    .Side
    16.50
    Activations Density 0.414%

    No Known Activations