© 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. 61280
    Prev
    Next
    INDEX
    Explanations

    using [word]

    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
    rik
    -0.09
    /use
    -0.09
    erp
    -0.08
     tendency
    -0.08
    ullan
    -0.08
    .live
    -0.08
    `()
    -0.08
    emetery
    -0.08
    ToUpdate
    -0.08
    ramework
    -0.07
    POSITIVE LOGITS
    bas
    0.09
    amp
    0.08
    advert
    0.08
     swear
    0.08
    pin
    0.08
    ajo
    0.08
     purely
    0.08
    assin
    0.08
     experiment
    0.08
    mie
    0.08
    Activations Density 0.075%

    No Known Activations