© 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. 14049
    Prev
    Next
    INDEX
    Explanations

    say geometry

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

    No Comments

    Negative Logits
    帘
    -18.50
    饯
    -17.25
    油
    -16.63
    便利店
    -16.25
    外卖
    -16.25
    机油
    -16.00
     Lana
    -15.81
     enviar
    -15.56
    smtp
    -15.44
     envi
    -15.44
    POSITIVE LOGITS
    几何
    28.75
     triangles
    28.13
     geomet
    27.63
     triangle
    27.38
     geometric
    27.13
    三角
    26.63
    Geometry
    25.88
     Geometry
    25.75
     geometry
    25.38
     triang
    25.13
    Activations Density 0.223%

    No Known Activations