© 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. 15758
    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
    郓
    -19.25
    绿城
    -18.13
     Akron
    -17.00
    Ｑ
    -16.63
     qx
    -16.63
    杭
    -16.50
     квар
    -16.25
    ánt
    -16.13
     Krak
    -15.75
    Ř
    -15.69
    POSITIVE LOGITS
    finger
    21.50
     Rope
    21.38
     hand
    21.13
    握手
    21.00
     finger
    20.25
    攀
    20.13
    hand
    20.13
     handshake
    19.38
     Hand
    18.88
     stream
    18.75
    Activations Density 0.268%

    No Known Activations