© 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. 3158
    Prev
    Next
    INDEX
    Explanations

    say system

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    空间
    -21.25
     Entry
    -19.38
     entry
    -19.13
    空間
    -19.00
     space
    -18.50
    Space
    -18.25
     Space
    -17.63
     nhập
    -17.38
    _entry
    -16.13
    (entry
    -15.94
    POSITIVE LOGITS
     system
    23.63
    system
    23.13
    体系
    22.38
    System
    22.38
    _system
    21.88
    系统
    21.75
    (system
    21.25
    	system
    20.63
     System
    19.88
    -system
    19.88
    Activations Density 0.005%

    No Known Activations