© 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. 2101
    Prev
    Next
    INDEX
    Explanations

    say detection

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

    No Comments

    Negative Logits
     Prop
    -18.13
     Der
    -17.13
     deriv
    -17.00
    围
    -16.50
     Sept
    -16.25
     erot
    -16.00
    der
    -15.75
     Replica
    -15.56
    PROP
    -15.56
    decor
    -15.56
    POSITIVE LOGITS
    检测
    45.75
    检验
    30.88
    檢
    30.88
    (det
    29.13
    检
    28.88
     det
    27.13
     detection
    25.25
    det
    25.13
    .det
    24.88
     Det
    23.25
    Activations Density 0.051%

    No Known Activations