© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 91745
    Prev
    Next
    INDEX
    Explanations

    lung and pulmonary function

    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
     scalp
    -0.11
     identities
    -0.10
     pil
    -0.10
    usher
    -0.09
     Jason
    -0.09
     sexually
    -0.09
     erection
    -0.09
     sanitation
    -0.09
    omen
    -0.09
     wrist
    -0.09
    POSITIVE LOGITS
     lung
    0.41
     lungs
    0.39
     Lung
    0.36
     bron
    0.35
     pulmonary
    0.33
     cough
    0.32
     Bron
    0.29
     respiratory
    0.28
     Respir
    0.28
     pneumonia
    0.28
    Activations Density 1.416%

    No Known Activations