© 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. 3194
    Prev
    Next
    INDEX
    Explanations

    equality

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    esan
    -16.75
     RelayCommand
    -16.63
    enal
    -15.50
    datagrid
    -15.19
    'action
    -14.88
    â
    -14.56
     territor
    -14.50
    éré
    -13.69
    inkel
    -13.56
     Component
    -13.50
    POSITIVE LOGITS
     equation
    39.75
    方
    38.50
     Equation
    35.50
     equations
    30.00
     equality
    24.50
    Equ
    24.38
    方に
    24.00
     LEVEL
    23.88
    equality
    23.50
     level
    23.38
    Activations Density 0.084%

    No Known Activations