© 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. 8925
    Prev
    Next
    INDEX
    Explanations

    nicknames or aliases

    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
    aders
    -0.08
     Letters
    -0.07
    )":
    -0.07
     Hearing
    -0.07
     Iris
    -0.07
    fell
    -0.07
     fingertips
    -0.07
    uars
    -0.07
    jal
    -0.07
     Maj
    -0.07
    POSITIVE LOGITS
     himself
    0.10
     aka
    0.10
    thead
    0.10
    arily
    0.09
    .eth
    0.09
    ATRIX
    0.09
     born
    0.09
     backstage
    0.08
     diagnoses
    0.08
     actor
    0.08
    Activations Density 0.428%

    No Known Activations