© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1124
    Prev
    Next
    INDEX
    Explanations

    diarrhea

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

    No Comments

    Negative Logits
     diarrhea
    -34.25
     diarr
    -30.13
    腹泻
    -28.50
     Di
    -24.63
    Di
    -23.88
     diag
    -23.63
    _diag
    -23.50
     diagonal
    -23.25
    di
    -23.13
     DIAG
    -22.38
    POSITIVE LOGITS
     Jewel
    18.13
    法律责任
    16.50
    angel
    16.13
     Angel
    16.00
    技术
    15.94
     jewel
    15.75
    кам
    15.56
    asin
    15.38
    ель
    15.25
     angel
    15.25
    Activations Density 0.127%

    No Known Activations