© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1474
    Prev
    Next
    INDEX
    Explanations

    do not say pictures

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

    No Comments

    Negative Logits
     pictures
    -42.00
     picture
    -42.00
     Picture
    -40.75
    图片
    -40.50
    picture
    -39.75
     Pictures
    -39.00
    Picture
    -38.25
    -picture
    -36.25
    Pictures
    -35.25
    圖片
    -35.25
    POSITIVE LOGITS
    创新
    20.13
     Israel
    17.38
     innovation
    17.13
    创新驱动
    17.00
     Innovation
    15.94
    不断创新
    15.38
     Innov
    14.88
    创新能力
    14.81
     innovations
    14.50
    引擎
    14.31
    Activations Density 0.065%

    No Known Activations