© 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. 8190
    Prev
    Next
    INDEX
    Explanations

    section symbol § or ³

    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
    eb
    -0.09
     =&
    -0.09
    achten
    -0.08
    python
    -0.08
    kov
    -0.08
    olle
    -0.08
    udd
    -0.08
    |#
    -0.08
    kö
    -0.08
    ————————
    -0.08
    POSITIVE LOGITS
     Fuller
    0.10
    amedi
    0.09
     Griff
    0.09
     Marketplace
    0.08
    afen
    0.08
    vara
    0.08
    seg
    0.08
     Pandora
    0.08
    Unified
    0.08
     Odyssey
    0.08
    Activations Density 0.011%

    No Known Activations