© 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. 2194
    Prev
    Next
    INDEX
    Explanations

    say 民

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

    No Comments

    Negative Logits
    perms
    -19.00
    tabs
    -18.38
    (pts
    -18.00
     Prescott
    -17.88
     Perkins
    -17.88
    给宝宝
    -17.75
     Tabs
    -17.50
    _Tab
    -17.38
    _tabs
    -17.38
     TAB
    -17.38
    POSITIVE LOGITS
    民
    53.25
     eth
    37.00
     civil
    31.25
     Civil
    30.88
     Eth
    30.50
    乙
    28.63
    Civil
    27.63
     civ
    27.13
    Eth
    26.13
    _eth
    26.00
    Activations Density 0.041%

    No Known Activations