© 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. 25156
    Prev
    Next
    INDEX
    Explanations

    duration and time periods

    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
     dilig
    -0.10
     Roth
    -0.09
    oser
    -0.09
    arget
    -0.09
     Invasion
    -0.09
    eki
    -0.09
     lei
    -0.09
    ago
    -0.09
    OCR
    -0.09
    avi
    -0.09
    POSITIVE LOGITS
     seconds
    0.12
     until
    0.12
     lasts
    0.12
     till
    0.11
     lasted
    0.11
    until
    0.11
     lasting
    0.10
    si
    0.10
    seconds
    0.10
     longer
    0.10
    Activations Density 0.045%

    No Known Activations