© 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. 61367
    Prev
    Next
    INDEX
    Explanations

    initials and abbreviations

    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
    oyal
    -0.09
     Zusammen
    -0.07
    uciones
    -0.07
     Laur
    -0.07
     Ramsey
    -0.06
    urf
    -0.06
     generics
    -0.06
    ohn
    -0.06
    summary
    -0.06
    serter
    -0.06
    POSITIVE LOGITS
     Decomp
    0.11
    arb
    0.11
    alie
    0.10
    asha
    0.10
    anyl
    0.10
    agas
    0.10
    adel
    0.10
    elight
    0.10
    .idea
    0.10
    anan
    0.10
    Activations Density 0.009%

    No Known Activations