© 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. 111494
    Prev
    Next
    INDEX
    Explanations

    government actions and pronouncements

    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
     personally
    -0.21
     volunteered
    -0.13
     wears
    -0.13
     wore
    -0.13
     Personally
    -0.13
     died
    -0.13
     wear
    -0.12
     attended
    -0.12
     testify
    -0.12
     volunteering
    -0.12
    POSITIVE LOGITS
     itself
    0.18
    -sponsored
    0.13
     internally
    0.13
     invested
    0.12
     releasing
    0.11
     subsid
    0.11
     wisely
    0.11
     announce
    0.11
     investing
    0.11
     send
    0.11
    Activations Density 1.529%

    No Known Activations