© 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. 89781
    Prev
    Next
    INDEX
    Explanations

    time words

    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
     Wilkinson
    -0.10
     immediately
    -0.09
    578
    -0.09
    INGER
    -0.09
     seriously
    -0.09
    inder
    -0.08
     Immediately
    -0.08
     instantly
    -0.08
     Huff
    -0.08
     ÑĥÑģпеÑĪ
    -0.08
    POSITIVE LOGITS
     tonight
    0.15
     today
    0.15
     recently
    0.14
    today
    0.13
     yesterday
    0.13
    Yesterday
    0.13
     Recently
    0.12
     sometimes
    0.12
     Today
    0.12
    Recently
    0.11
    Activations Density 0.009%

    No Known Activations