© 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. 16331
    Prev
    Next
    INDEX
    Explanations

    say year

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

    No Comments

    Negative Logits
    dzi
    -19.13
     dz
    -18.50
     DST
    -17.88
    tz
    -17.63
    胧
    -17.25
     tattoo
    -16.63
    tent
    -16.63
    zb
    -16.63
     crawled
    -16.63
    .tpl
    -16.38
    POSITIVE LOGITS
    _years
    34.50
    年
    34.50
    年报
    33.75
     years
    33.50
    year
    33.25
     year
    33.00
    年的
    32.75
    years
    32.25
     YEARS
    32.25
    _year
    31.88
    Activations Density 0.352%

    No Known Activations

    This feature has no known activations.