© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15109
    Prev
    Next
    INDEX
    Explanations

    say "侵略" words

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

    No Comments

    Negative Logits
    arrière
    -17.25
     Autof
    -16.25
     kitt
    -16.25
    educt
    -16.13
    Draft
    -15.44
     deduction
    -15.38
    declar
    -15.00
    че
    -14.88
     draft
    -14.69
     Resolver
    -14.69
    POSITIVE LOGITS
    入侵
    19.75
    攻击
    19.38
    侵略
    18.75
    侵
    18.00
    庄
    17.88
    进攻
    17.88
    实施
    16.88
     invasion
    16.88
    控制
    16.88
    攻
    16.75
    Activations Density 0.116%

    No Known Activations