© 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. 1838
    Prev
    Next
    INDEX
    Explanations

    medical and healthcare information

    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
    /facebook
    -0.09
    ~~
    -0.09
    ky
    -0.08
    abra
    -0.08
     pent
    -0.08
    sky
    -0.08
     recon
    -0.08
     Memorial
    -0.08
     rookies
    -0.07
    layer
    -0.07
    POSITIVE LOGITS
     care
    0.12
    -care
    0.12
    /ph
    0.11
     spas
    0.10
    /dis
    0.10
     Disclaimer
    0.10
    .nlm
    0.10
    /path
    0.10
     Care
    0.10
    ehr
    0.10
    Activations Density 1.751%

    No Known Activations