© 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. 117615
    Prev
    Next
    INDEX
    Explanations

    people with roles or conditions

    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
    ola
    -0.09
     Newman
    -0.09
    ikk
    -0.08
    OLA
    -0.08
     Sisters
    -0.07
    iek
    -0.07
    igu
    -0.07
    /conf
    -0.07
    GL
    -0.07
    acks
    -0.07
    POSITIVE LOGITS
     proponents
    0.14
     afflicted
    0.13
     implementing
    0.12
     manifestation
    0.12
     associated
    0.12
     adopting
    0.12
     sufferers
    0.12
    ivi
    0.11
     practitioners
    0.11
     involved
    0.11
    Activations Density 0.709%

    No Known Activations