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

    Neuronpedia

    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. 670
    Prev
    Next
    INDEX
    Explanations

    say hepatitis

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

    No Comments

    Negative Logits
    德州
    -22.38
    花卉
    -21.75
     Flores
    -20.50
    花瓣
    -20.13
    伊斯兰
    -20.00
     Santos
    -19.63
     Sultan
    -19.13
     Karachi
    -19.13
     Cologne
    -18.75
    Islam
    -18.75
    POSITIVE LOGITS
     Hep
    36.00
    肝
    32.00
     hepat
    30.75
     HB
    30.25
     hepatitis
    29.50
    乙肝
    28.38
    辽宁
    28.13
     liver
    27.88
    吉林省
    26.63
    朝鲜
    26.50
    Activations Density 0.052%

    No Known Activations