© 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. 61412
    Prev
    Next
    INDEX
    Explanations

    first partition, return new

    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
     Slim
    -0.11
    azi
    -0.10
     Raphael
    -0.10
     ado
    -0.10
     Mane
    -0.09
    HW
    -0.09
     lengths
    -0.09
    liga
    -0.09
    -www
    -0.09
     Humph
    -0.08
    POSITIVE LOGITS
    arna
    0.08
    ToFront
    0.08
    -initialized
    0.08
     mixed
    0.07
    éĩ
    0.07
    zs
    0.07
    BUR
    0.07
     kern
    0.07
     credibility
    0.07
    =format
    0.07
    Activations Density 0.005%

    No Known Activations