© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2472
    Prev
    Next
    INDEX
    Explanations

    速

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

    No Comments

    Negative Logits
    镜子
    -19.25
    机关
    -18.63
    reflection
    -18.50
     Reflection
    -18.38
     bis
    -17.88
    Pres
    -17.63
     reflection
    -17.50
    機構
    -17.50
    .Tab
    -17.38
    Mirror
    -17.00
    POSITIVE LOGITS
    速
    29.75
     seq
    21.88
    (seq
    21.13
     pos
    21.00
     ret
    19.88
     newPos
    19.63
    [pos
    19.38
    .vel
    18.75
    .Pos
    18.75
    pos
    18.75
    Activations Density 0.038%

    No Known Activations