© 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. 4812
    Prev
    Next
    INDEX
    Explanations

    description and data fields

    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
     lif
    -0.10
    rosso
    -0.10
     fal
    -0.10
    endo
    -0.10
     Tang
    -0.10
     Townsend
    -0.09
     endpoint
    -0.09
     Verg
    -0.09
     frankfurt
    -0.09
     subrange
    -0.09
    POSITIVE LOGITS
     Indicates
    0.09
     description
    0.08
     handwritten
    0.08
    æııè¿°
    0.08
     flags
    0.08
    flags
    0.08
    quina
    0.07
     notes
    0.07
     coded
    0.07
    /code
    0.07
    Activations Density 0.121%

    No Known Activations