© 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. 15092
    Prev
    Next
    INDEX
    Explanations

    say "7"

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

    No Comments

    Negative Logits
    柒
    -19.75
    七
    -18.38
     seven
    -17.25
     Seven
    -17.00
     cook
    -16.88
    7
    -16.88
     cuc
    -16.75
     bounty
    -16.63
    seven
    -16.50
    郅
    -16.50
    POSITIVE LOGITS
    ERP
    18.75
     phosphate
    16.63
    erate
    16.13
    FPS
    16.13
    rophy
    15.94
    VRT
    15.88
    iphy
    15.75
    erp
    15.75
     Harris
    15.56
     CAT
    15.44
    Activations Density 0.027%

    No Known Activations