© 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. 3178
    Prev
    Next
    INDEX
    Explanations

    say "use"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     utilizing
    -27.50
     UTIL
    -26.75
    (Util
    -25.75
     utilized
    -25.38
    (util
    -24.88
    	util
    -24.63
    util
    -24.25
     utilizando
    -23.63
     Util
    -22.38
    UTIL
    -22.00
    POSITIVE LOGITS
     use
    52.00
    Use
    47.25
     Use
    47.00
    use
    44.50
    使用
    44.25
    _use
    43.25
    .use
    41.50
    	use
    41.25
    -use
    39.25
    (use
    37.25
    Activations Density 0.588%

    No Known Activations