© 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. 3098
    Prev
    Next
    INDEX
    Explanations

    say "digit"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    文件
    -23.25
     files
    -22.75
     file
    -22.38
    方向
    -21.00
    _files
    -19.13
     File
    -18.50
    -file
    -18.38
    _file
    -17.88
     文件
    -17.88
    odox
    -17.50
    POSITIVE LOGITS
    SYSTEM
    18.25
    Parameter
    18.13
    =line
    18.00
    -group
    17.25
     combination
    17.13
    (parameter
    16.88
     line
    16.75
    模型
    16.75
     Farr
    16.75
    TableRow
    16.63
    Activations Density 0.121%

    No Known Activations