© 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. 3133
    Prev
    Next
    INDEX
    Explanations

    say "purpose/value"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    行
    -24.50
    Line
    -19.25
     Line
    -19.00
     line
    -18.75
    _line
    -16.88
    line
    -16.63
    面板
    -16.13
    组
    -15.38
    -panel
    -15.25
    各行
    -15.19
    POSITIVE LOGITS
    purpose
    22.38
    价值
    21.63
     process
    20.38
     purpose
    18.25
    过程
    18.13
     Stephen
    17.38
     Purpose
    17.13
    價值
    17.13
     scope
    17.00
    	process
    17.00
    Activations Density 0.049%

    No Known Activations