© 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. 3179
    Prev
    Next
    INDEX
    Explanations

    [time] => [to]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    元素
    -19.63
    -family
    -18.13
    案
    -17.63
    区
    -17.50
    Family
    -16.38
    family
    -16.25
    Solution
    -16.25
    _level
    -16.25
    _scheme
    -16.25
    分布
    -16.13
    POSITIVE LOGITS
    module
    18.88
     character
    18.13
    component
    18.00
    Module
    18.00
     Module
    17.63
     module
    17.50
     component
    17.13
     viewpoint
    17.00
    -module
    16.63
    睢
    16.63
    Activations Density 0.267%

    No Known Activations