© 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. 14107
    Prev
    Next
    INDEX
    Explanations

    say "homemade"

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

    No Comments

    Negative Logits
    分析
    -18.50
    数据分析
    -18.13
    立法
    -17.38
    推进
    -17.13
     legislators
    -17.13
    analysis
    -17.00
     treaties
    -16.88
     PARAM
    -16.63
     analysis
    -16.50
     Legisl
    -16.50
    POSITIVE LOGITS
     kits
    17.38
     Kitchen
    16.38
    kit
    16.38
     homemade
    16.25
    Kitchen
    16.13
    家装
    15.94
    买到
    15.88
     Kits
    15.56
     kitchen
    15.44
    锉
    14.81
    Activations Density 0.530%

    No Known Activations