© 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. 4877
    Prev
    Next
    INDEX
    Explanations

    hypertension and blood pressure control

    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
    bart
    -0.09
    antal
    -0.09
     stav
    -0.09
    raft
    -0.09
    olan
    -0.09
     Fletcher
    -0.09
    rust
    -0.08
    ohana
    -0.08
     pes
    -0.08
     dens
    -0.08
    POSITIVE LOGITS
    aq
    0.09
    irate
    0.09
    usal
    0.09
     hypertension
    0.08
    atory
    0.08
    qué
    0.08
    ension
    0.08
     Ky
    0.08
     control
    0.08
    control
    0.07
    Activations Density 0.129%

    No Known Activations