© 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. 14273
    Prev
    Next
    INDEX
    Explanations

    say "record"

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

    No Comments

    Negative Logits
    TestFixture
    -14.75
    .setOutput
    -14.69
    CGRect
    -14.56
    hões
    -14.38
     Pear
    -14.38
    engu
    -14.19
    .squareup
    -14.19
    agan
    -14.06
     brides
    -14.00
    ї
    -14.00
    POSITIVE LOGITS
    记录
    82.00
     record
    75.00
     records
    73.50
    record
    70.00
    纪录
    69.50
     Record
    67.50
     Records
    66.50
    Record
    66.00
    records
    65.00
    -record
    62.75
    Activations Density 1.656%

    No Known Activations