© 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. 3198
    Prev
    Next
    INDEX
    Explanations

    say file metadata

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    矩阵
    -18.25
     �
    -16.88
     tableau
    -16.38
    forcement
    -15.63
     matrix
    -15.00
    (configuration
    -14.94
    テー�
    -14.94
     Buffer
    -14.94
    	matrix
    -14.94
    Ë
    -14.88
    POSITIVE LOGITS
    部门
    17.25
    时间
    16.88
    文件
    16.50
    ListModel
    16.13
     files
    16.00
     departments
    15.75
     file
    15.44
     company
    15.31
     department
    15.19
     filetype
    15.19
    Activations Density 0.054%

    No Known Activations