© 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. 14143
    Prev
    Next
    INDEX
    Explanations

    say toys

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

    No Comments

    Negative Logits
    信息技术
    -16.63
     cemetery
    -15.44
    个人信息
    -15.25
    宣言
    -15.25
    vation
    -15.06
    绛
    -14.94
    mination
    -14.81
    KHTML
    -14.75
    采访时
    -14.63
     frequencies
    -14.31
    POSITIVE LOGITS
    玩具
    25.25
     Toys
    25.00
     toys
    22.88
     games
    22.88
     Play
    22.75
    玩
    22.25
    トイ
    22.13
     plastic
    22.00
     Toy
    22.00
    教育培训
    21.38
    Activations Density 0.210%

    No Known Activations