© 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. 14222
    Prev
    Next
    INDEX
    Explanations

    say population

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

    No Comments

    Negative Logits
    产品研发
    -23.75
    模型
    -20.38
    产品质量
    -20.25
    产品
    -19.88
    折扣
    -19.13
    價
    -19.00
    订单
    -19.00
    产品的
    -18.13
     product
    -18.00
    打折
    -18.00
    POSITIVE LOGITS
     population
    18.88
     populations
    18.38
     living
    18.38
     live
    18.25
    living
    18.00
     Census
    17.88
     registrations
    17.50
     Registration
    17.38
    อาศ
    17.25
    population
    17.00
    Activations Density 0.608%

    No Known Activations