© 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. 2199
    Prev
    Next
    INDEX
    Explanations

    say "admin"

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

    No Comments

    Negative Logits
    assin
    -15.63
     ctor
    -14.44
     Fort
    -14.38
     fig
    -14.38
    篮
    -14.19
    手套
    -14.06
    Nonnull
    -14.06
    复发
    -13.63
    -cond
    -13.50
    Fort
    -13.44
    POSITIVE LOGITS
     admin
    78.50
    行政
    75.00
     Admin
    73.50
    admin
    73.00
    (admin
    72.50
    	admin
    72.00
    Admin
    69.50
    .admin
    68.00
     administrative
    68.00
     administr
    67.50
    Activations Density 0.310%

    No Known Activations