© 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. 3369
    Prev
    Next
    INDEX
    Explanations

    journal titles and abbreviations

    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
     pand
    -0.10
     Confeder
    -0.10
     conce
    -0.10
    /Register
    -0.09
    Sea
    -0.09
    avit
    -0.09
     UNITY
    -0.09
     overt
    -0.09
    Broad
    -0.09
    adesh
    -0.09
    POSITIVE LOGITS
     Journal
    0.40
    Journal
    0.34
     journal
    0.33
     journals
    0.25
    journal
    0.25
     Proceedings
    0.24
    Proceed
    0.21
     Ann
    0.21
     Bulletin
    0.21
     J
    0.20
    Activations Density 1.639%

    No Known Activations