© 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. 2931
    Prev
    Next
    INDEX
    Explanations

    say "ethnic"

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

    No Comments

    Negative Logits
    笔
    -16.25
    庄
    -15.88
    管
    -15.81
     reg
    -15.56
    ellers
    -15.38
     med
    -15.19
     Peninsula
    -15.19
    贝壳
    -14.88
    秦皇
    -14.88
     Simulator
    -14.44
    POSITIVE LOGITS
    乙
    61.00
    Eth
    60.50
     Eth
    60.00
     eth
    55.00
    eth
    54.25
    _eth
    48.50
    .eth
    47.50
     ethical
    47.00
     ethnic
    46.75
    ETH
    46.50
    Activations Density 0.114%

    No Known Activations