© 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. 3309
    Prev
    Next
    INDEX
    Explanations

    say search

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    部
    -18.63
     module
    -17.75
    模块
    -17.50
    单位
    -16.38
    .module
    -16.38
     vực
    -15.69
    module
    -15.69
    _module
    -15.50
     SG
    -15.38
    variable
    -15.25
    POSITIVE LOGITS
     search
    56.25
    搜索
    52.00
    search
    48.75
     Search
    46.75
    Search
    45.75
    _search
    44.00
    	search
    43.50
    .search
    43.00
    (search
    43.00
    -search
    41.00
    Activations Density 0.033%

    No Known Activations