© 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. 30588
    Prev
    Next
    INDEX
    Explanations

    medical residency and education

    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
    æ²»
    -0.14
     technician
    -0.14
     appointments
    -0.14
     therapist
    -0.13
     Salon
    -0.13
     treatment
    -0.13
     counseling
    -0.13
     counselor
    -0.13
     appointment
    -0.12
     client
    -0.12
    POSITIVE LOGITS
     residency
    0.19
     pager
    0.16
     rotations
    0.15
     IMG
    0.14
     Resident
    0.13
     Pager
    0.13
     Residents
    0.13
     rotation
    0.13
     scrub
    0.13
     residents
    0.12
    Activations Density 1.010%

    No Known Activations