© 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. 4801
    Prev
    Next
    INDEX
    Explanations

    complex numbers and formulas

    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
    emy
    -0.11
     Sto
    -0.10
    ustr
    -0.10
     Emm
    -0.10
     Gibbs
    -0.10
     Tyr
    -0.09
    ubi
    -0.09
     Buen
    -0.09
    igram
    -0.09
     Watch
    -0.09
    POSITIVE LOGITS
     valued
    0.09
    -val
    0.09
    yk
    0.09
    isce
    0.08
    kie
    0.08
    enna
    0.08
    sla
    0.08
    nev
    0.07
     privately
    0.07
    hop
    0.07
    Activations Density 0.083%

    No Known Activations