© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48757
    Prev
    Next
    INDEX
    Explanations

    visual appeal and aesthetics

    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
    Not in Any Lists

    No Comments

    Negative Logits
    avin
    -0.09
    gom
    -0.09
     hastily
    -0.09
     Burlington
    -0.09
    ernet
    -0.09
    oples
    -0.08
     @$_
    -0.08
     Choice
    -0.08
    651
    -0.08
    elay
    -0.08
    POSITIVE LOGITS
     visually
    0.57
     aest
    0.55
     aesthetic
    0.54
     aesthetics
    0.52
     visual
    0.45
     decorative
    0.43
     visuals
    0.41
     decoration
    0.34
     beaut
    0.34
     Visual
    0.33
    Activations Density 1.088%

    No Known Activations