© 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. 1934
    Prev
    Next
    INDEX
    Explanations

    risk

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

    No Comments

    Negative Logits
    风险
    -48.75
     risk
    -46.00
    风险管理
    -44.25
     Risk
    -43.75
    Risk
    -43.25
     risks
    -41.75
    風險
    -41.00
    的风险
    -40.25
    risk
    -39.75
     Ris
    -39.00
    POSITIVE LOGITS
    adium
    16.00
    mac
    15.56
    氢
    14.31
     Panama
    13.81
    /mac
    13.63
     web
    13.50
     Seoul
    13.44
    Web
    13.25
    phere
    13.13
     Earth
    13.13
    Activations Density 0.185%

    No Known Activations