© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2302
    Prev
    Next
    INDEX
    Explanations

    say civil

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tab
    -20.50
     repos
    -19.00
     repo
    -19.00
    (tab
    -18.50
    (repo
    -18.25
    	tab
    -17.75
    repo
    -17.38
    .tab
    -17.13
    tab
    -17.13
     Tab
    -17.00
    POSITIVE LOGITS
    民
    56.25
     civil
    40.25
    民众
    40.00
     Civil
    37.25
    Civil
    37.00
     civilian
    33.75
    civil
    33.25
     dân
    32.75
     civ
    32.75
    民用
    31.38
    Activations Density 0.179%

    No Known Activations