© 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. 49447
    Prev
    Next
    INDEX
    Explanations

    time of day or week

    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
     nowadays
    -0.13
     yearly
    -0.13
     annually
    -0.12
     someday
    -0.12
     winters
    -0.11
     today
    -0.11
     summers
    -0.11
    ä¸Ģ页
    -0.10
     Oper
    -0.10
     periodically
    -0.10
    POSITIVE LOGITS
    /month
    0.10
     Klo
    0.09
     morning
    0.09
     afternoon
    0.08
     lunch
    0.08
     when
    0.08
     Blank
    0.08
    -after
    0.08
    rey
    0.08
    ory
    0.08
    Activations Density 0.100%

    No Known Activations