© 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. 8329
    Prev
    Next
    INDEX
    Explanations

    section numbering or identifiers

    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
     Vict
    -0.09
     FAQ
    -0.08
    dex
    -0.07
     built
    -0.07
     Gloss
    -0.07
     Bosch
    -0.07
     Crowley
    -0.07
     Vin
    -0.07
     right
    -0.07
     Myth
    -0.07
    POSITIVE LOGITS
    ood
    0.12
     SEEK
    0.10
    stown
    0.10
    RAP
    0.10
     nou
    0.10
    ilk
    0.10
     riv
    0.09
    oba
    0.09
    ibs
    0.09
    ench
    0.09
    Activations Density 0.032%

    No Known Activations