© 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. 3249
    Prev
    Next
    INDEX
    Explanations

    [br] => ]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Table
    -20.88
     Parameters
    -20.38
     Group
    -19.63
    集团
    -19.63
    Table
    -19.63
     Groups
    -18.38
    组
    -18.00
     Parameter
    -18.00
    Group
    -17.63
     Company
    -17.38
    POSITIVE LOGITS
    (space
    18.63
     view
    17.00
    ��
    16.88
    _handling
    16.88
    (region
    16.75
     файл
    16.63
     файла
    16.38
     $
↵
    16.25
    [file
    16.25
    view
    16.25
    Activations Density 0.176%

    No Known Activations