© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 695
    Prev
    Next
    INDEX
    Explanations

    say Korean particles

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

    No Comments

    Negative Logits
    宜昌
    -22.00
    峡
    -16.25
     Cleveland
    -16.13
    Detroit
    -15.44
    三峡
    -15.13
    ✝
    -14.81
    rá
    -14.75
    뉠
    -14.44
    _:*
    -14.38
    常德
    -14.19
    POSITIVE LOGITS
    가
    27.00
     기
    23.38
    에
    23.25
    의
    22.88
     �
    22.88
    이
    22.63
     단
    22.63
     �
    22.63
     �
    22.63
    도
    22.38
    Activations Density 0.073%

    No Known Activations

    This feature has no known activations.