© 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. 3114
    Prev
    Next
    INDEX
    Explanations

    say "sector"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    闳
    -17.63
    ikit
    -17.13
     SCC
    -16.75
    .Sdk
    -15.94
    KC
    -15.69
     McMahon
    -15.56
    (sr
    -15.31
    幔
    -15.31
    GOR
    -14.88
    orer
    -14.81
    POSITIVE LOGITS
     sector
    52.25
     Sector
    43.25
    sector
    43.25
    Sector
    39.75
     sectors
    36.75
    -sector
    36.75
     section
    36.00
    _sector
    33.50
    section
    32.00
    .section
    30.38
    Activations Density 0.042%

    No Known Activations