© 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. 3146
    Prev
    Next
    INDEX
    Explanations

    year

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    device
    -22.63
     device
    -22.63
    .device
    -20.38
     Device
    -20.00
    evice
    -19.75
    /device
    -19.00
    -device
    -19.00
    Device
    -18.63
    	device
    -18.63
    signal
    -18.50
    POSITIVE LOGITS
     year
    59.25
     Year
    53.75
    year
    53.25
    Year
    53.00
    _year
    48.50
    年
    46.00
    .year
    43.75
     YEAR
    42.00
    -year
    41.50
    年的
    41.25
    Activations Density 0.217%

    No Known Activations