© 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. 18602
    Prev
    Next
    INDEX
    Explanations

    consumer and processing

    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
     deployed
    -0.15
     deployment
    -0.14
     deploy
    -0.14
     deploying
    -0.14
     Deployment
    -0.13
     deployments
    -0.13
     Deploy
    -0.13
     rede
    -0.12
    Deployment
    -0.12
    deploy
    -0.11
    POSITIVE LOGITS
     Melissa
    0.37
     consumer
    0.23
     consumers
    0.21
     metabolism
    0.21
     Consumer
    0.21
    Consumer
    0.20
     metabolic
    0.19
    consumer
    0.19
     Consumers
    0.19
     market
    0.18
    Activations Density 0.093%

    No Known Activations