© 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. 3318
    Prev
    Next
    INDEX
    Explanations

    say "equation"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Artist
    -17.88
     filmmaker
    -17.13
     artist
    -16.75
    ắc
    -16.38
    artist
    -15.75
     Artists
    -15.50
    生物科技
    -15.50
    辘
    -15.50
    movies
    -15.31
     layer
    -15.06
    POSITIVE LOGITS
     equation
    89.00
     Equation
    77.50
    方
    73.50
     equations
    71.00
    Equ
    56.25
    equ
    46.25
    _equ
    46.25
     方
    43.00
    式
    42.00
     Equ
    41.00
    Activations Density 0.077%

    No Known Activations