© 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. 58966
    Prev
    Next
    INDEX
    Explanations

    try to [verb]

    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
     desper
    -0.10
     cord
    -0.09
     divers
    -0.09
    elo
    -0.09
     Serial
    -0.09
     leverage
    -0.08
    .Input
    -0.08
     dust
    -0.08
     Laf
    -0.08
     emphasis
    -0.08
    POSITIVE LOGITS
    олов
    0.10
     aggreg
    0.09
    reas
    0.09
    kon
    0.09
     Kol
    0.09
     tens
    0.08
    compress
    0.08
     sud
    0.08
     unresolved
    0.08
    bers
    0.08
    Activations Density 0.025%

    No Known Activations