© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 222
    Prev
    Next
    INDEX
    Explanations

    medical experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Businesses
    -0.11
     Dise
    -0.10
     superf
    -0.10
     Zuk
    -0.09
     monet
    -0.09
     gum
    -0.09
     ail
    -0.09
     businesses
    -0.09
     forsk
    -0.09
     competit
    -0.09
    POSITIVE LOGITS
     clinical
    0.17
    clinical
    0.15
     practice
    0.15
     guidelines
    0.15
     Practice
    0.15
     Clinical
    0.14
     guideline
    0.14
     clinicians
    0.14
     patient
    0.14
     patients
    0.13
    Activations Density 5.423%

    No Known Activations