© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111385
    Prev
    Next
    INDEX
    Explanations

    Adobe Photoshop and Illustrator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     unm
    -0.10
     inters
    -0.09
     pom
    -0.09
    fos
    -0.09
    Embed
    -0.09
     recomm
    -0.09
     hypnot
    -0.08
     pacing
    -0.08
     Thur
    -0.08
     carr
    -0.08
    POSITIVE LOGITS
     Photoshop
    0.18
     Adobe
    0.18
    Adobe
    0.15
     photoshop
    0.15
    edImage
    0.10
    ellido
    0.10
    /photos
    0.10
    obe
    0.10
    AIR
    0.10
     FI
    0.10
    Activations Density 0.080%

    No Known Activations