© 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. 3347
    Prev
    Next
    INDEX
    Explanations

    say digits

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    建华
    -16.25
    ë
    -16.25
    秉
    -16.13
     référence
    -16.00
     khoản
    -15.88
    邨
    -15.31
    參考
    -15.19
     hiếm
    -15.19
    люч
    -14.94
    ,label
    -14.88
    POSITIVE LOGITS
     Area
    24.88
     Component
    20.00
    Area
    19.88
     Result
    19.50
    area
    19.38
    Areas
    19.00
     area
    18.63
    Component
    18.63
     Application
    18.50
     result
    18.38
    Activations Density 0.038%

    No Known Activations