© 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. 3216
    Prev
    Next
    INDEX
    Explanations

    say "<"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Equation
    -26.13
     equation
    -25.50
    system
    -24.63
     system
    -22.38
    systems
    -21.75
    系统
    -21.13
    System
    -21.13
    	system
    -20.75
     System
    -20.63
    path
    -20.38
    POSITIVE LOGITS
    模型
    18.50
     model
    18.00
    osite
    16.75
     models
    16.63
    _models
    16.13
    _model
    15.94
    ely
    15.63
    モデル
    15.31
    侧
    15.19
    model
    15.13
    Activations Density 0.080%

    No Known Activations