© 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. 1880
    Prev
    Next
    INDEX
    Explanations

    say stock

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

    No Comments

    Negative Logits
     fontStyle
    -18.75
     Urdu
    -18.50
    orum
    -18.25
     GRAPH
    -18.00
     Lawn
    -17.75
    诗句
    -17.50
     cavalry
    -17.38
    河西
    -17.38
     graphs
    -17.25
    詩
    -17.25
    POSITIVE LOGITS
     stock
    19.13
    =log
    17.88
     Stock
    17.38
    Stock
    17.25
    stock
    17.25
     STOCK
    16.25
    stocks
    16.13
     Svens
    15.88
     log
    15.81
     Alpha
    15.81
    Activations Density 0.402%

    No Known Activations