© 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. 16365
    Prev
    Next
    INDEX
    Explanations

    say plaque

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

    No Comments

    Negative Logits
    GAN
    -18.50
    反转
    -17.13
    ProductId
    -16.50
     Bauer
    -16.00
    BUY
    -15.94
    宸
    -15.56
    =rand
    -15.19
    投资项目
    -15.13
    (expect
    -15.06
    渔
    -15.06
    POSITIVE LOGITS
     plaque
    19.38
    堵塞
    16.88
    粥
    16.63
    窄
    16.38
    狭窄
    16.25
     pla
    16.13
    硬化
    15.94
    硬
    15.75
    Calc
    15.75
     plug
    15.69
    Activations Density 0.076%

    No Known Activations