© 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. 15702
    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
    oton
    -17.63
    breadcrumb
    -16.88
    URY
    -16.75
     Tags
    -16.75
     tags
    -16.50
     Huff
    -16.38
    ueue
    -15.94
     euler
    -15.88
    /tags
    -15.88
    (Tag
    -15.88
    POSITIVE LOGITS
     hand
    54.50
    的手
    51.00
    手
    51.00
    hand
    50.25
     hands
    49.25
     Hand
    48.75
    Hand
    46.00
     Hands
    43.75
    _hand
    43.25
    .hand
    43.25
    Activations Density 0.320%

    No Known Activations