© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15651
    Prev
    Next
    INDEX
    Explanations

    say calendar

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

    No Comments

    Negative Logits
    bucket
    -20.75
    _bucket
    -20.75
     bucket
    -20.63
    网购
    -19.50
    空军
    -18.88
     buckets
    -18.75
    Bucket
    -18.63
    .bucket
    -18.63
    Paint
    -18.63
     Paint
    -18.63
    POSITIVE LOGITS
     calendars
    27.88
     calendar
    25.25
     calend
    24.88
     Calendar
    24.00
    -calendar
    23.75
    (calendar
    23.63
    calendar
    22.63
    Calendar
    22.50
    -Cal
    21.50
    _calendar
    21.25
    Activations Density 0.266%

    No Known Activations