© 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. 117211
    Prev
    Next
    INDEX
    Explanations

    paint and coating surfaces

    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
     implanted
    -0.11
     floppy
    -0.11
     quota
    -0.10
     shard
    -0.10
     crystal
    -0.10
     Bil
    -0.10
     Blackburn
    -0.10
    EMS
    -0.10
     Wol
    -0.09
     Kro
    -0.09
    POSITIVE LOGITS
     paint
    0.34
     repaint
    0.29
     painting
    0.29
    paint
    0.28
     Paint
    0.27
     primer
    0.26
    Paint
    0.26
     painted
    0.26
     painters
    0.25
     Painting
    0.24
    Activations Density 0.321%

    No Known Activations