© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28755
    Prev
    Next
    INDEX
    Explanations

    late night hours

    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
    arus
    -0.09
    ibili
    -0.09
    ulary
    -0.08
     Frozen
    -0.08
     Burke
    -0.08
     Daily
    -0.08
     Fleming
    -0.08
    iston
    -0.08
     frozen
    -0.08
     Zimmer
    -0.08
    POSITIVE LOGITS
     late
    0.26
     overnight
    0.26
    late
    0.22
     Late
    0.22
     Overnight
    0.21
     nights
    0.21
    overn
    0.20
    Late
    0.19
     night
    0.17
     laten
    0.17
    Activations Density 0.034%

    No Known Activations