© 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. 1411
    Prev
    Next
    INDEX
    Explanations

    [first name] => [last name]

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

    No Comments

    Negative Logits
     engineering
    -20.88
    particle
    -20.38
     engineer
    -20.00
    科学
    -19.88
    science
    -19.75
    engineering
    -19.75
    scientific
    -19.50
     Scientific
    -19.13
     Clyde
    -19.13
     Engineer
    -19.00
    POSITIVE LOGITS
    浏览器
    18.00
    军
    17.00
    有毒
    16.88
     browsers
    16.75
    噪声
    15.69
     noise
    15.38
     JSX
    15.19
     css
    15.06
     CSS
    15.00
     Browser
    14.94
    Activations Density 0.219%

    No Known Activations