© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1058
    Prev
    Next
    INDEX
    Explanations

    [electricity] => [electricity]

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

    No Comments

    Negative Logits
     electricity
    -36.00
     Electricity
    -32.75
    Electric
    -31.63
    electric
    -31.38
     electrical
    -29.25
     electric
    -28.13
     Electrical
    -27.38
    电气
    -26.38
     Electric
    -26.25
    能量
    -25.00
    POSITIVE LOGITS
    宫
    15.88
    宮
    15.25
    /firebase
    14.56
    .firebase
    14.44
     Kart
    14.13
     font
    13.94
    ▻
    13.63
     Zen
    13.44
    .paper
    13.44
    珠
    13.31
    Activations Density 0.035%

    No Known Activations