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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15504
    Prev
    Next
    INDEX
    Explanations

    say "repression"

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

    No Comments

    Negative Logits
    -fly
    -18.25
    金币
    -16.50
    交易平台
    -16.25
    Fly
    -16.13
    惫
    -16.00
    虚空
    -15.88
     millionaire
    -15.88
     Chevy
    -15.69
    umper
    -15.63
    为空
    -15.56
    POSITIVE LOGITS
     suppression
    19.50
     suppress
    19.25
     crackdown
    18.25
     purge
    18.13
     censor
    18.00
    打压
    18.00
    镇
    17.75
    压制
    17.38
     repression
    17.25
     censorship
    17.00
    Activations Density 0.377%

    No Known Activations