© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31695
    Prev
    Next
    INDEX
    Explanations

    medical professions and specialties

    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
     imperson
    -0.10
     bloody
    -0.10
    Universal
    -0.09
     Classroom
    -0.09
     Asi
    -0.09
     nurs
    -0.09
     deactivated
    -0.09
    /Math
    -0.09
     Scout
    -0.09
    .ribbon
    -0.08
    POSITIVE LOGITS
     specialty
    0.25
     specialties
    0.22
     specialization
    0.21
     specialists
    0.21
     Specialty
    0.21
     Specialists
    0.20
     specialist
    0.20
     obst
    0.19
     specialize
    0.19
     Specialist
    0.19
    Activations Density 4.692%

    No Known Activations