© 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. 61182
    Prev
    Next
    INDEX
    Explanations

    p-type and n-type

    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
    oni
    -0.10
     pur
    -0.08
     Venez
    -0.08
    Comm
    -0.08
    ono
    -0.07
     Immun
    -0.07
     yeast
    -0.07
     reversible
    -0.07
     Kavanaugh
    -0.06
     Boiler
    -0.06
    POSITIVE LOGITS
    fcn
    0.10
    elves
    0.10
    icia
    0.09
    ece
    0.09
    inki
    0.09
    DER
    0.09
    .uf
    0.09
    itter
    0.09
    ense
    0.09
    naments
    0.09
    Activations Density 0.003%

    No Known Activations