© 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. 53746
    Prev
    Next
    INDEX
    Explanations

    for (its, a, me, sure, the)

    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
    phen
    -0.08
    elder
    -0.08
    pent
    -0.08
     purely
    -0.08
    lier
    -0.08
    holm
    -0.08
    ius
    -0.08
    icter
    -0.08
    gress
    -0.08
    ë§Į
    -0.08
    POSITIVE LOGITS
     Somebody
    0.10
     somebody
    0.09
    ADD
    0.09
     Tender
    0.08
    ucs
    0.08
    ublic
    0.08
    aes
    0.08
    ubes
    0.08
     Helsinki
    0.08
    (es
    0.08
    Activations Density 0.043%

    No Known Activations