© 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. 87757
    Prev
    Next
    INDEX
    Explanations

    ok sequences

    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
     critically
    -0.10
     provision
    -0.10
    enor
    -0.10
     repl
    -0.09
     nas
    -0.09
     domestically
    -0.09
     Provision
    -0.09
     literal
    -0.09
    ikal
    -0.09
     dep
    -0.09
    POSITIVE LOGITS
     equip
    0.11
     Arsenal
    0.10
    advisor
    0.10
     equipo
    0.10
    ffa
    0.10
    aden
    0.09
    esa
    0.09
    anye
    0.09
    Nav
    0.09
    ulist
    0.09
    Activations Density 0.008%

    No Known Activations