© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117530
    Prev
    Next
    INDEX
    Explanations

    documentation files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    abee
    -0.10
    bang
    -0.10
     bang
    -0.10
     Fel
    -0.09
     fel
    -0.09
     ser
    -0.09
     Lois
    -0.08
     Kas
    -0.08
    iswa
    -0.08
     Pra
    -0.08
    POSITIVE LOGITS
    quat
    0.10
    -ul
    0.09
    /dashboard
    0.09
    assi
    0.09
    -driven
    0.09
    apon
    0.09
    (vol
    0.09
    amt
    0.09
    /manual
    0.09
     Bucc
    0.09
    Activations Density 0.001%

    No Known Activations