© 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. 2588
    Prev
    Next
    INDEX
    Explanations

    funds

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

    No Comments

    Negative Logits
    .aws
    -20.75
     radios
    -20.25
     trains
    -20.13
     train
    -19.38
     cigarette
    -19.13
    发货
    -19.00
     lung
    -18.75
    车厢
    -18.63
     cigarettes
    -18.63
     plantation
    -18.50
    POSITIVE LOGITS
     fund
    25.63
    基金经理
    23.88
    基金
    22.63
    基金管理
    20.50
     funds
    19.50
    投资
    19.00
    投资基金
    18.75
     Funds
    18.75
     Fund
    18.63
    资金
    18.50
    Activations Density 0.168%

    No Known Activations