© 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. 53742
    Prev
    Next
    INDEX
    Explanations

    code initialization patterns

    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
     trunc
    -0.10
    æĪ
    -0.10
    issa
    -0.10
    ango
    -0.09
    phant
    -0.09
    inho
    -0.09
    -close
    -0.08
    odor
    -0.08
    ubar
    -0.08
     truncated
    -0.08
    POSITIVE LOGITS
     Henrik
    0.09
    /module
    0.08
     Donovan
    0.08
    hek
    0.08
     Mane
    0.08
    llib
    0.08
     ris
    0.08
    oud
    0.08
     vim
    0.08
     Bobby
    0.08
    Activations Density 0.008%

    No Known Activations