© 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. 15798
    Prev
    Next
    INDEX
    Explanations

    say hand

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

    No Comments

    Negative Logits
     Atlantis
    -21.13
     Dek
    -20.75
    APH
    -20.75
    乌鲁
    -19.88
    phan
    -19.88
     Ebony
    -18.88
    沁
    -18.75
    碣
    -18.75
    陵
    -18.25
     PHI
    -18.13
    POSITIVE LOGITS
    的手
    21.75
    disp
    17.25
    手上
    16.50
     distancing
    15.88
    清醒
    15.81
    fur
    15.81
    胳膊
    15.56
     brush
    15.38
    臂
    15.38
    豕
    15.25
    Activations Density 1.890%

    No Known Activations