© 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. 50717
    Prev
    Next
    INDEX
    Explanations

    economic growth and jobs

    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
    Not in Any Lists

    No Comments

    Negative Logits
     scrap
    -0.10
     cust
    -0.09
     personality
    -0.09
    /hash
    -0.09
     Funeral
    -0.09
     legality
    -0.09
    uito
    -0.09
     custody
    -0.09
     roman
    -0.09
     verbal
    -0.09
    POSITIVE LOGITS
     economic
    0.49
     economy
    0.46
     Economic
    0.41
     Economy
    0.39
     economies
    0.39
    economic
    0.37
     GDP
    0.36
     economically
    0.35
     Econom
    0.35
     jobs
    0.34
    Activations Density 1.151%

    No Known Activations