© 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. 50827
    Prev
    Next
    INDEX
    Explanations

    adjectives describing people

    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
     grues
    -0.14
     blat
    -0.13
    rightness
    -0.13
     uncomment
    -0.13
     anonymously
    -0.12
     egreg
    -0.12
     unmist
    -0.12
     amateurs
    -0.12
    onium
    -0.11
     damning
    -0.11
    POSITIVE LOGITS
     intelligent
    0.23
     outgoing
    0.23
     smart
    0.18
     knowledgeable
    0.18
     adventurous
    0.17
     caring
    0.17
     assert
    0.16
     ambitious
    0.16
     intelig
    0.16
     talented
    0.16
    Activations Density 0.033%

    No Known Activations