© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3215
    Prev
    Next
    INDEX
    Explanations

    say "date"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    structure
    -21.25
     Structure
    -20.00
     structure
    -19.13
     structures
    -18.88
    结构
    -18.50
    Structure
    -17.88
    _structure
    -17.75
    模型
    -17.25
     Structures
    -17.25
    .structure
    -17.25
    POSITIVE LOGITS
     date
    69.00
    date
    60.75
    日期
    57.75
     Date
    55.00
    Date
    54.25
    _date
    53.50
    	date
    53.00
    .date
    52.75
    (date
    51.50
    -date
    50.50
    Activations Density 0.136%

    No Known Activations