© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14189
    Prev
    Next
    INDEX
    Explanations

    say registration

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

    No Comments

    Negative Logits
    产品
    -19.25
    设计师
    -17.88
     product
    -17.63
    销售人员
    -16.75
    类产品
    -16.63
     designers
    -16.50
    的产品
    -16.38
    产品经理
    -16.13
    Product
    -15.94
     ProductService
    -15.75
    POSITIVE LOGITS
     registration
    26.13
     regist
    25.75
     Registration
    25.50
    注册
    25.50
     register
    25.50
    -registration
    25.25
     registrations
    25.13
     registry
    24.50
     registering
    24.25
     Registers
    24.25
    Activations Density 0.620%

    No Known Activations