© 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. 13917
    Prev
    Next
    INDEX
    Explanations

    say selection

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

    No Comments

    Negative Logits
    elta
    -17.63
     patriotic
    -17.13
    Government
    -17.13
    政府采购
    -17.13
    posted
    -16.63
    项目建设
    -16.63
    ẳng
    -16.25
    箔
    -16.13
    政府
    -16.13
     Government
    -16.13
    POSITIVE LOGITS
     selection
    26.88
     Selection
    25.00
    Selection
    24.13
     survival
    24.00
     Darwin
    23.75
    Surv
    22.88
    选
    22.88
    生存
    22.75
     Survival
    22.75
     sélection
    22.38
    Activations Density 0.488%

    No Known Activations