© 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. 13907
    Prev
    Next
    INDEX
    Explanations

    duration or time period

    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
     reflex
    -0.11
    Opts
    -0.09
    asa
    -0.09
    nder
    -0.09
     Wah
    -0.09
     Reflex
    -0.09
     Farr
    -0.08
    asma
    -0.08
    ppo
    -0.08
     Wort
    -0.08
    POSITIVE LOGITS
     day
    0.29
     weekend
    0.29
     overnight
    0.27
     afternoon
    0.24
    day
    0.22
     weekends
    0.22
    -day
    0.21
     Weekend
    0.21
     hour
    0.21
     Day
    0.21
    Activations Density 0.117%

    No Known Activations