© 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. 3352
    Prev
    Next
    INDEX
    Explanations

    say ":"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    政府
    -19.50
    =file
    -18.88
     chapter
    -17.63
    	file
    -16.75
    (file
    -16.75
    CUS
    -16.38
    政府部门
    -16.38
    ,file
    -16.13
    ysi
    -16.00
    的眼光
    -16.00
    POSITIVE LOGITS
     community
    21.50
    社区
    20.38
    community
    19.88
    Community
    19.75
     Community
    19.25
     system
    19.13
    系统
    19.00
    系统的
    17.50
     System
    17.25
    _system
    16.38
    Activations Density 0.223%

    No Known Activations