© 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. 3120
    Prev
    Next
    INDEX
    Explanations

    configuration

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    poly
    -15.75
     onAnimation
    -15.38
    egrity
    -14.88
    وبا
    -14.56
    头脑
    -14.56
    schools
    -14.56
    族自治县
    -14.56
    道
    -14.44
     inflate
    -14.31
    群体
    -14.31
    POSITIVE LOGITS
     configuration
    69.50
    configuration
    66.00
     Configuration
    61.00
    Configuration
    59.75
    _configuration
    57.00
    配置
    55.00
    (configuration
    54.50
     configurations
    51.50
    .configuration
    50.25
    /configuration
    45.25
    Activations Density 0.112%

    No Known Activations