© 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. 18557
    Prev
    Next
    INDEX
    Explanations

    medical terminology and concepts

    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
     grieving
    -0.12
     survivors
    -0.12
     recovered
    -0.12
    ardon
    -0.12
     recovering
    -0.12
     Charges
    -0.11
     depressed
    -0.11
     wounded
    -0.11
    Bookmark
    -0.11
     injured
    -0.11
    POSITIVE LOGITS
     medical
    0.17
     doctor
    0.16
     ambulance
    0.14
     physician
    0.13
     Medical
    0.13
     doctors
    0.12
    medical
    0.12
     medicine
    0.11
     medic
    0.11
     diagnostic
    0.11
    Activations Density 0.268%

    No Known Activations