© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8656
    Prev
    Next
    INDEX
    Explanations

    pharmaceuticals and prescriptions

    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
    Negative Logits
     intermitt
    -0.10
    ific
    -0.09
    gage
    -0.09
    cate
    -0.09
    ogy
    -0.08
    atu
    -0.08
    ¥
    -0.08
    uite
    -0.08
    ikes
    -0.08
    ENTA
    -0.08
    POSITIVE LOGITS
     medicines
    0.13
    Drug
    0.13
     drug
    0.13
     Drug
    0.13
     medications
    0.12
    drug
    0.12
     Drugs
    0.11
     Medic
    0.11
     medication
    0.11
    aceut
    0.11
    Activations Density 0.405%

    No Known Activations