© 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. 8294
    Prev
    Next
    INDEX
    Explanations

    college and education paths

    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
    iste
    -0.10
     Burl
    -0.10
     anonymously
    -0.10
     interle
    -0.09
     Physiology
    -0.09
     male
    -0.09
    opaque
    -0.09
     relocate
    -0.09
    anel
    -0.09
     relocated
    -0.09
    POSITIVE LOGITS
     college
    0.19
     colleges
    0.14
    college
    0.14
     educ
    0.13
     higher
    0.12
     tertiary
    0.12
     collage
    0.12
     coll
    0.11
     education
    0.11
    -educated
    0.11
    Activations Density 0.125%

    No Known Activations