© 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. 3111
    Prev
    Next
    INDEX
    Explanations

    say system

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ís
    -14.25
    izzle
    -14.06
     Smy
    -13.63
    尧
    -13.56
    (sym
    -13.50
    emodel
    -13.50
     stringify
    -13.44
    rowing
    -13.44
    opoulos
    -13.31
    quette
    -13.25
    POSITIVE LOGITS
    系统
    107.00
     system
    105.00
    system
    98.50
    系统的
    98.50
     System
    94.50
    System
    94.00
    (system
    89.50
    _system
    88.50
    	system
    88.50
    -system
    87.50
    Activations Density 1.142%

    No Known Activations