© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15427
    Prev
    Next
    INDEX
    Explanations

    say "image"

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

    No Comments

    Negative Logits
     pipes
    -18.50
    bootstrap
    -18.38
    爐
    -18.00
     sleeve
    -17.88
     smoker
    -17.75
     smtp
    -17.63
     Fireplace
    -17.38
     slump
    -17.38
     armour
    -17.25
    东风
    -17.13
    POSITIVE LOGITS
    原
    18.38
    影像
    18.00
    信息
    17.75
    数
    17.00
    图像
    16.88
    IM
    16.75
    作业
    16.63
    黑白
    16.50
    照
    16.38
    灰
    16.38
    Activations Density 0.138%

    No Known Activations