© 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. 3110
    Prev
    Next
    INDEX
    Explanations

    path

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    	field
    -18.75
     COMPANY
    -18.50
    [field
    -18.00
     field
    -17.88
    field
    -17.88
    (field
    -17.13
    company
    -17.13
    	side
    -16.75
    .field
    -16.25
    Company
    -16.13
    POSITIVE LOGITS
     Path
    26.25
    Path
    25.25
    .Path
    25.00
     path
    25.00
    -path
    24.63
    路径
    24.38
     paths
    24.13
    /path
    22.88
    path
    22.75
    _path
    21.38
    Activations Density 0.174%

    No Known Activations