© 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. 3167
    Prev
    Next
    INDEX
    Explanations

    say "city"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Ey
    -18.63
     component
    -18.25
     Component
    -17.88
    Component
    -17.88
    _component
    -17.50
    组件
    -17.50
    .component
    -16.63
    range
    -16.25
     range
    -15.94
    component
    -15.94
    POSITIVE LOGITS
    市
    57.50
    市の
    40.50
    市政府
    36.00
    全市
    32.75
     city
    32.50
    市委
    31.75
     City
    31.13
    市中心
    30.13
    市教育
    29.75
    市长
    28.38
    Activations Density 0.063%

    No Known Activations