© 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. 3169
    Prev
    Next
    INDEX
    Explanations

    say end token

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Module
    -21.88
     module
    -21.38
    Module
    -17.75
    module
    -17.63
     link
    -17.50
     form
    -17.25
     box
    -16.75
     answer
    -16.38
    .module
    -16.25
    例
    -16.25
    POSITIVE LOGITS
    组织
    21.38
     setObject
    18.50
     organization
    17.63
    _organization
    17.50
    Organization
    17.50
    組織
    16.88
    班级
    16.75
     organización
    16.75
     getObject
    16.75
     organisation
    16.75
    Activations Density 0.066%

    No Known Activations