© 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. 1393
    Prev
    Next
    INDEX
    Explanations

    [electric] => [noun]

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

    No Comments

    Negative Logits
     electric
    -23.25
    electric
    -22.75
     Electric
    -22.25
     electrical
    -20.38
    Electric
    -19.75
    vector
    -18.88
    电动
    -18.13
    电气
    -18.00
    _vector
    -17.00
    .vector
    -16.88
    POSITIVE LOGITS
     mediation
    16.88
     med
    16.13
    -paper
    16.00
    _paper
    16.00
    Paper
    15.94
     paper
    15.44
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    15.44
    PA
    15.19
     wine
    15.00
    Lang
    14.94
    Activations Density 0.049%

    No Known Activations