© 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. 1575
    Prev
    Next
    INDEX
    Explanations

    电压

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

    No Comments

    Negative Logits
    电压
    -38.00
    Voltage
    -36.75
     Voltage
    -36.50
     voltage
    -35.00
    _VOLT
    -31.13
    _voltage
    -28.25
    Volt
    -25.13
     Volt
    -24.13
     volt
    -23.88
    oltage
    -23.75
    POSITIVE LOGITS
    är
    15.38
     искусств
    14.38
    ary
    14.38
     Gaming
    14.25
     Artificial
    13.56
     Arrow
    13.38
     arts
    13.38
     Games
    13.19
    麦
    13.06
     gam
    13.00
    Activations Density 0.060%

    No Known Activations