© 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. 61174
    Prev
    Next
    INDEX
    Explanations

    (b) followed by parenthesis

    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
     LIMITED
    -0.08
    ets
    -0.07
    hy
    -0.06
    pread
    -0.06
    SHA
    -0.06
    PN
    -0.06
     limited
    -0.06
    tas
    -0.06
     flavored
    -0.06
     enroll
    -0.06
    POSITIVE LOGITS
     Humph
    0.11
     sécur
    0.10
    à¹Į
    0.10
    :auto
    0.10
    ournée
    0.10
    ibur
    0.10
    orra
    0.10
    uhe
    0.10
    _private
    0.10
     Gar
    0.10
    Activations Density 0.001%

    No Known Activations