© 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. 1254
    Prev
    Next
    INDEX
    Explanations

    [criminal] => [criminal]

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

    No Comments

    Negative Logits
     criminal
    -32.00
     crime
    -29.25
     Crime
    -28.38
     criminals
    -27.13
    犯罪
    -26.50
    Crime
    -25.75
     Criminal
    -25.00
    刑事案件
    -24.50
    岩石
    -24.00
    stone
    -23.88
    POSITIVE LOGITS
     σ
    14.06
    ソフト
    13.94
     ED
    13.94
    南海
    13.88
     eigen
    13.81
     software
    13.75
    σ
    13.69
     Eigen
    13.63
    .ix
    13.63
     Diagram
    13.50
    Activations Density 0.069%

    No Known Activations