© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31936
    Prev
    Next
    INDEX
    Explanations

    times of day or meals

    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
     tantal
    -0.10
    chas
    -0.09
     shortage
    -0.09
     explan
    -0.09
     Interr
    -0.09
     unfamiliar
    -0.09
     ctr
    -0.09
     INDIRECT
    -0.09
     Exhaust
    -0.09
     eta
    -0.09
    POSITIVE LOGITS
     lunch
    0.25
     morning
    0.23
     breakfast
    0.23
     daily
    0.22
     nightly
    0.21
     afternoon
    0.20
     evening
    0.20
     Lunch
    0.19
     dinner
    0.18
     Breakfast
    0.18
    Activations Density 0.231%

    No Known Activations