© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14221
    Prev
    Next
    INDEX
    Explanations

    say "people"

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

    No Comments

    Negative Logits
    -entry
    -21.63
     entry
    -21.00
    entry
    -20.75
     Entry
    -19.88
    课程
    -18.75
    _entry
    -18.75
     entries
    -18.75
    法律顾问
    -18.50
    	entry
    -18.25
    _Entry
    -18.13
    POSITIVE LOGITS
    群众
    27.25
    民众
    27.13
    人民群众
    24.50
    百姓
    23.63
    民眾
    23.38
     populace
    23.00
     citizens
    22.00
     populations
    22.00
     population
    21.63
    pop
    21.50
    Activations Density 0.801%

    No Known Activations