© 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. 13894
    Prev
    Next
    INDEX
    Explanations

    time remaining or duration

    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
     recently
    -0.12
    recent
    -0.10
     gradually
    -0.10
     yesterday
    -0.09
     eventually
    -0.09
    eps
    -0.09
     promptly
    -0.08
     nig
    -0.08
     Recently
    -0.08
    Recently
    -0.08
    POSITIVE LOGITS
     deadline
    0.14
     retirement
    0.12
     sunset
    0.12
     adulthood
    0.12
    ermann
    0.11
     Mandatory
    0.11
     eternity
    0.11
     till
    0.10
     Retirement
    0.10
     mandatory
    0.10
    Activations Density 0.059%

    No Known Activations