© 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. 1581
    Prev
    Next
    INDEX
    Explanations

    say company names

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

    No Comments

    Negative Logits
     Microsoft
    -47.75
    Microsoft
    -44.50
    微软
    -38.50
     microsoft
    -36.00
    .microsoft
    -34.25
    /windows
    -31.13
    .Microsoft
    -31.13
     Windows
    -30.13
    icrosoft
    -29.88
     MS
    -29.50
    POSITIVE LOGITS
     сах
    16.88
    anton
    16.38
     Alg
    16.38
    香
    16.13
    法律
    15.81
    基因
    15.81
    埃及
    15.56
    苏州
    15.38
     sugar
    14.75
     gene
    14.75
    Activations Density 0.159%

    No Known Activations