© 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. 3096
    Prev
    Next
    INDEX
    Explanations

    say "0"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    路径
    -18.88
    日期
    -18.25
     groups
    -17.63
    groups
    -17.38
    Groups
    -17.25
    modelName
    -17.13
    村
    -17.00
    集团
    -16.63
    岁月
    -16.50
     时间
    -16.38
    POSITIVE LOGITS
     class
    24.50
     Class
    24.25
     point
    23.50
    点
    21.88
     Point
    20.88
    _CLASS
    20.88
    (point
    20.88
    .point
    20.75
    _point
    20.63
    class
    20.38
    Activations Density 0.098%

    No Known Activations