© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1344
    Prev
    Next
    INDEX
    Explanations

    justice

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

    No Comments

    Negative Logits
     justice
    -31.63
    Japan
    -30.13
    JavaScript
    -30.13
    Javascript
    -29.88
    Journal
    -29.75
     Japan
    -29.75
     JS
    -29.38
    司法
    -29.25
    JS
    -29.13
    Java
    -29.13
    POSITIVE LOGITS
     vo
    13.81
    是一件
    13.81
    Mac
    13.81
    安全保障
    13.31
     Voice
    13.06
    ycz
    12.69
     voice
    12.63
    .voice
    12.25
    vc
    12.13
    łę
    12.13
    Activations Density 0.547%

    No Known Activations