© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14142
    Prev
    Next
    INDEX
    Explanations

    say moral concepts

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

    No Comments

    Negative Logits
    技术支持
    -19.13
    organization
    -18.75
    分子
    -18.50
     organiz
    -18.38
    组织
    -18.38
    QE
    -18.25
     organization
    -18.25
    _organization
    -17.50
    ationToken
    -17.25
    organ
    -17.13
    POSITIVE LOGITS
     estates
    13.69
    白白
    13.00
     deeds
    12.88
     distributions
    12.63
     lord
    12.56
    mods
    12.31
     mock
    12.19
     War
    12.19
     wars
    12.06
     generous
    12.06
    Activations Density 0.627%

    No Known Activations