© 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. 16652
    Prev
    Next
    INDEX
    Explanations

    time references

    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
     someday
    -0.16
     annually
    -0.13
     yearly
    -0.13
     Nowadays
    -0.11
     eventual
    -0.11
     annual
    -0.11
     eventually
    -0.10
     year
    -0.10
     Year
    -0.10
     Annual
    -0.10
    POSITIVE LOGITS
     earlier
    0.66
     Earlier
    0.50
    Earlier
    0.47
     previously
    0.42
     yesterday
    0.39
     previous
    0.38
     preceding
    0.32
     Previously
    0.32
     beforehand
    0.32
    Previously
    0.31
    Activations Density 0.543%

    No Known Activations