© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 603
    Prev
    Next
    INDEX
    Explanations

    say Adobe Photoshop

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

    No Comments

    Negative Logits
     alcoholic
    -20.13
    地中海
    -19.88
     Mediterranean
    -19.88
    .dense
    -19.75
     booze
    -19.50
     vodka
    -18.75
    红薯
    -18.50
    穰
    -18.38
     garlic
    -18.25
     sperma
    -18.25
    POSITIVE LOGITS
     Photoshop
    32.75
     Adobe
    31.50
    Adobe
    30.00
     photoshop
    28.25
    Photos
    27.75
     Illustrator
    24.88
    艺术
    22.25
     artwork
    21.75
     art
    21.13
    Creative
    21.13
    Activations Density 0.099%

    No Known Activations