© 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. 18684
    Prev
    Next
    INDEX
    Explanations

    time and events

    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
     soon
    -0.14
     skipped
    -0.13
     skipping
    -0.13
     Soon
    -0.12
     weeks
    -0.11
     upcoming
    -0.11
     days
    -0.11
     impending
    -0.11
     postponed
    -0.10
    qv
    -0.10
    POSITIVE LOGITS
     arrival
    0.15
     arrive
    0.12
     departure
    0.11
     rou
    0.11
     expected
    0.10
     leaving
    0.10
     finished
    0.10
     arriving
    0.10
     arrivals
    0.10
     Arrival
    0.10
    Activations Density 0.091%

    No Known Activations