© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15691
    Prev
    Next
    INDEX
    Explanations

    say digital

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

    No Comments

    Negative Logits
    裁定
    -18.25
    queues
    -17.75
    血液
    -17.13
    htm
    -17.00
    太后
    -16.38
    问候
    -16.00
    帘
    -16.00
    eventId
    -15.81
    htt
    -15.81
    大妈
    -15.56
    POSITIVE LOGITS
    数字化
    24.75
     Digital
    24.38
    数字
    24.00
     digital
    23.88
     Digit
    23.50
     digit
    22.88
    Digital
    22.75
     digitally
    21.63
    digital
    21.50
    -digit
    21.13
    Activations Density 0.168%

    No Known Activations