© 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. 3106
    Prev
    Next
    INDEX
    Explanations

    say "multiplication"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    _coeff
    -17.00
     Frame
    -17.00
    文件
    -16.38
    _frame
    -16.25
    节点
    -16.13
     node
    -15.94
    组
    -15.94
    -file
    -15.81
     frame
    -15.75
    raq
    -15.75
    POSITIVE LOGITS
    query
    18.63
     query
    17.38
    .query
    16.25
    /query
    15.94
     queries
    15.06
    	query
    14.81
    查询
    14.75
     pData
    14.50
     queried
    14.38
     data
    14.25
    Activations Density 0.023%

    No Known Activations