© 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. 1876
    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
     email
    -52.75
     Email
    -52.00
    Email
    -52.00
     emails
    -50.75
    email
    -49.75
    _email
    -49.50
    	email
    -47.00
    _EMAIL
    -46.50
    电子邮件
    -46.25
    邮件
    -46.00
    POSITIVE LOGITS
    几何
    19.13
     geometry
    17.88
     geometric
    17.63
    (geometry
    16.38
    _geometry
    15.94
     Geometry
    15.88
    Triangle
    15.25
     gé
    14.38
    Geometry
    14.31
     Sang
    14.31
    Activations Density 0.071%

    No Known Activations