© 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. 3312
    Prev
    Next
    INDEX
    Explanations

    say "times"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     cur
    -18.88
    	cur
    -17.13
     regime
    -16.75
     Gen
    -15.44
    曲
    -15.00
    erm
    -14.81
    wild
    -14.69
    Curr
    -14.63
    xe
    -14.44
    [cur
    -14.44
    POSITIVE LOGITS
     hex
    23.50
    .hex
    22.25
    hex
    22.13
    _hex
    20.50
    times
    20.13
    (hex
    19.50
    .times
    19.38
    Hex
    19.13
     idx
    18.75
     times
    18.63
    Activations Density 0.004%

    No Known Activations