© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2823
    Prev
    Next
    INDEX
    Explanations

    say "util"

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

    No Comments

    Negative Logits
     usado
    -15.63
    魔
    -14.38
    emin
    -14.25
     usar
    -14.19
     sourceMappingURL
    -14.13
    新的一
    -13.75
     caut
    -13.50
    iset
    -13.44
     Braz
    -13.44
     mint
    -13.38
    POSITIVE LOGITS
    (util
    87.00
     util
    84.50
     Util
    82.50
    util
    81.50
    Util
    80.00
    	util
    79.50
    (Util
    79.00
    利用
    79.00
     utilization
    70.00
    _util
    68.00
    Activations Density 0.497%

    No Known Activations