© 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. 91292
    Prev
    Next
    INDEX
    Explanations

    medical injuries and emergencies

    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
     outright
    -0.11
     Neville
    -0.10
     unchecked
    -0.10
     Ville
    -0.10
     blatantly
    -0.10
    Acceler
    -0.09
     bully
    -0.09
     skim
    -0.09
     wholesale
    -0.09
    Messenger
    -0.09
    POSITIVE LOGITS
     emergency
    0.26
     hospital
    0.26
     hospitalized
    0.23
     Emergency
    0.23
     ambulance
    0.22
    Emergency
    0.22
     medical
    0.22
     hospitals
    0.21
     Hospital
    0.21
     doctors
    0.20
    Activations Density 0.271%

    No Known Activations