© 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. 14165
    Prev
    Next
    INDEX
    Explanations

    say shape words

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

    No Comments

    Negative Logits
    配
    -17.88
    推广应用
    -17.25
    服务机构
    -17.25
     Goal
    -17.13
    .GetService
    -16.50
    DataTask
    -16.38
    ��
    -16.13
    .goal
    -15.94
    -service
    -15.88
    .getService
    -15.75
    POSITIVE LOGITS
     shape
    22.13
     shaping
    21.25
    shape
    20.75
     shapes
    20.50
     Shape
    20.13
    Shape
    19.63
     Shapes
    19.38
     shaped
    19.25
    shapes
    18.13
    _SHAPE
    17.88
    Activations Density 0.805%

    No Known Activations