© 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. 33923
    Prev
    Next
    INDEX
    Explanations

    work hours and schedules

    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
    Not in Any Lists

    No Comments

    Negative Logits
     wells
    -0.09
     untouched
    -0.08
    warts
    -0.08
    oki
    -0.07
    Unauthorized
    -0.07
    itol
    -0.07
    ema
    -0.07
    udded
    -0.07
     Peterson
    -0.07
     repro
    -0.07
    POSITIVE LOGITS
     schedules
    0.45
     schedule
    0.44
     Schedule
    0.34
     hours
    0.34
     scheduling
    0.33
     flexible
    0.31
    schedule
    0.31
     Hours
    0.30
    Schedule
    0.30
     timetable
    0.29
    Activations Density 0.280%

    No Known Activations