© 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. 3218
    Prev
    Next
    INDEX
    Explanations

    say issue

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    path
    -19.38
    Path
    -18.00
     path
    -17.88
    路径
    -17.50
    	path
    -16.25
    -path
    -16.13
    .Path
    -15.94
    _path
    -15.75
    重量
    -15.63
    启迪
    -15.50
    POSITIVE LOGITS
     issue
    56.25
     Issue
    50.50
    Issue
    47.50
    issue
    46.25
    _issue
    42.75
    (issue
    42.50
    -issue
    40.25
     issues
    39.25
    .issue
    36.50
     Issues
    36.25
    Activations Density 0.124%

    No Known Activations