© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14108
    Prev
    Next
    INDEX
    Explanations

    say fund

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

    No Comments

    Negative Logits
     training
    -19.00
     authenticate
    -17.88
    training
    -17.88
     Training
    -17.63
    训练
    -17.25
    培训
    -17.25
    Training
    -17.00
     diagnostics
    -17.00
     prediction
    -16.88
     getConnection
    -16.88
    POSITIVE LOGITS
    资产管理
    26.38
    投资基金
    23.25
    资管
    21.50
    /assets
    20.75
    产品的
    20.50
    资产
    20.38
    基金
    20.13
    投资
    20.00
     fund
    20.00
    基金经理
    19.63
    Activations Density 0.281%

    No Known Activations