© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15287
    Prev
    Next
    INDEX
    Explanations

    say product

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

    No Comments

    Negative Logits
    感染者
    -17.13
     networks
    -16.88
    水面
    -16.75
    圆
    -16.25
     biologist
    -16.25
    渗
    -16.13
    闾
    -16.00
    源
    -15.94
    Sphere
    -15.88
    腐
    -15.81
    POSITIVE LOGITS
     products
    33.75
     product
    32.25
    产品
    31.63
    产品的
    30.88
    products
    30.88
    -product
    30.63
    product
    30.50
     Products
    30.50
    產品
    30.13
     productId
    29.63
    Activations Density 0.114%

    No Known Activations