© 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. 3294
    Prev
    Next
    INDEX
    Explanations

    say "digits"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     parameter
    -22.50
     PROPERTY
    -22.25
    DataManager
    -21.88
     property
    -21.38
    数据
    -20.75
     Parameter
    -20.50
    Property
    -19.50
     DataManager
    -19.50
    的数据
    -19.38
     Property
    -19.13
    POSITIVE LOGITS
     field
    18.88
    	field
    17.75
    field
    17.13
     area
    16.88
    area
    16.75
    箱
    16.75
    	area
    16.38
    -field
    16.13
    [field
    16.13
    .box
    15.88
    Activations Density 0.266%

    No Known Activations