© 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. 2387
    Prev
    Next
    INDEX
    Explanations

    say "detect"

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

    No Comments

    Negative Logits
    弘
    -16.13
     LIB
    -15.69
    YN
    -15.50
     lib
    -15.50
    .Lib
    -15.44
    民族
    -15.38
    Phil
    -15.06
    道士
    -15.06
     administr
    -14.94
     refin
    -14.94
    POSITIVE LOGITS
    (det
    69.00
    检测
    66.00
     detector
    65.50
    det
    65.00
     det
    61.25
    .det
    61.00
    detector
    61.00
     detectors
    60.75
    -det
    60.75
     Detector
    60.25
    Activations Density 0.268%

    No Known Activations