© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15776
    Prev
    Next
    INDEX
    Explanations

    say finance

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

    No Comments

    Negative Logits
     kisses
    -15.75
    ọ
    -15.44
     subdivision
    -14.81
    军官
    -14.44
     ε
    -14.06
     kho
    -13.88
    kad
    -13.44
     mỹ
    -13.38
    addElement
    -13.25
     analyses
    -13.00
    POSITIVE LOGITS
    融资
    22.50
     finance
    21.00
    的资金
    20.88
    资金
    20.63
    模式
    20.25
    平台
    20.00
    金融
    19.88
     circular
    19.88
    筹集
    19.38
    資金
    19.13
    Activations Density 0.227%

    No Known Activations