© 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. 3346
    Prev
    Next
    INDEX
    Explanations

    code snippets

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     pair
    -20.00
     distribution
    -19.75
     interface
    -19.75
    interface
    -18.25
     place
    -16.88
     Died
    -16.25
     branch
    -16.13
     Distribution
    -16.00
     method
    -15.81
     structure
    -15.44
    POSITIVE LOGITS
    项目的
    15.00
    该公司
    15.00
    mania
    14.50
    STACK
    14.19
    /problem
    13.94
     FILES
    13.56
    FileChooser
    13.50
    atoria
    13.31
     edited
    13.31
     targeted
    13.31
    Activations Density 0.266%

    No Known Activations