© 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. 1912
    Prev
    Next
    INDEX
    Explanations

    formula

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

    No Comments

    Negative Logits
     Formula
    -45.00
     formula
    -44.50
    公式
    -43.00
    formula
    -43.00
    Formula
    -43.00
     formulas
    -40.75
    _formula
    -39.50
     formul
    -25.38
     форму
    -24.13
     FM
    -22.50
    POSITIVE LOGITS
    港口
    16.50
    河边
    15.44
    /fire
    15.00
    经济
    15.00
    Linux
    14.75
     Psych
    14.56
    中国经济
    14.50
    ügen
    14.44
    土地
    14.25
    港
    14.13
    Activations Density 0.089%

    No Known Activations