© 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. 113722
    Prev
    Next
    INDEX
    Explanations

    duration related to years

    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
     Weeks
    -0.16
     Months
    -0.15
    -month
    -0.14
    Month
    -0.13
    Months
    -0.13
     Month
    -0.13
    (month
    -0.13
    Week
    -0.13
     Earlier
    -0.12
     month
    -0.12
    POSITIVE LOGITS
     decades
    0.38
     years
    0.33
     decade
    0.33
    years
    0.24
     Years
    0.23
    Years
    0.23
     YEARS
    0.20
    _years
    0.20
     twenty
    0.19
     centuries
    0.18
    Activations Density 0.316%

    No Known Activations