© 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. 1528
    Prev
    Next
    INDEX
    Explanations

    say social

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

    No Comments

    Negative Logits
    鹽
    -16.50
    阅
    -16.13
    erti
    -15.44
    croll
    -15.06
     Petroleum
    -15.06
    盐
    -15.00
    谄
    -14.88
     Hồng
    -14.81
    可想
    -14.81
    盐城
    -14.75
    POSITIVE LOGITS
     legal
    17.25
     Soc
    15.50
     SS
    15.50
    社會
    15.06
    社会
    14.88
    法律
    14.50
    tos
    14.25
     socially
    13.81
    �
    13.69
    SS
    13.13
    Activations Density 0.132%

    No Known Activations