© 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. 1616
    Prev
    Next
    INDEX
    Explanations

    patient selection and eligibility

    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
     someday
    -0.11
     even
    -0.10
     perhaps
    -0.10
     millions
    -0.09
     maybe
    -0.09
     somewhere
    -0.09
     billions
    -0.09
     really
    -0.08
     like
    -0.08
     something
    -0.08
    POSITIVE LOGITS
     randomly
    0.15
     eligible
    0.14
     selected
    0.12
     blinded
    0.12
     consenting
    0.12
     anonym
    0.11
     deemed
    0.11
     baseline
    0.11
     underwent
    0.11
     randomized
    0.11
    Activations Density 2.695%

    No Known Activations