© 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. 13961
    Prev
    Next
    INDEX
    Explanations

    stroke motion

    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
     stabbed
    -0.10
     orally
    -0.10
    zin
    -0.10
     punches
    -0.10
     knees
    -0.09
     footing
    -0.09
    ragen
    -0.09
     positioning
    -0.09
    omat
    -0.09
     punching
    -0.09
    POSITIVE LOGITS
     strokes
    0.19
     stroke
    0.17
     slow
    0.17
     Stroke
    0.16
     rhythm
    0.16
     stopping
    0.13
    Stroke
    0.13
    stroke
    0.13
    -strokes
    0.13
     palm
    0.13
    Activations Density 0.021%

    No Known Activations