© 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. 2319
    Prev
    Next
    INDEX
    Explanations

    stock market

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

    No Comments

    Negative Logits
    湄
    -19.50
    ystate
    -18.75
    GRAY
    -17.63
    主任
    -15.94
    桫
    -15.88
    ingham
    -15.56
    副局长
    -15.50
    SR
    -15.50
    西红
    -15.44
     poly
    -15.38
    POSITIVE LOGITS
     carriers
    15.75
    …I
    15.13
    auer
    15.13
    ại
    14.75
     car
    14.69
     puppy
    14.63
    Car
    14.19
    ListComponent
    13.44
    şim
    13.38
     nữa
    13.38
    Activations Density 0.060%

    No Known Activations