© 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. 6371
    Prev
    Next
    INDEX
    Explanations

    years and age

    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
     comm
    -0.10
     far
    -0.09
    ec
    -0.09
    /cl
    -0.09
    able
    -0.08
    rn
    -0.08
    Intermediate
    -0.08
    egov
    -0.08
    mo
    -0.08
    cha
    -0.08
    POSITIVE LOGITS
     age
    0.15
    imet
    0.10
     Age
    0.10
    _age
    0.10
     date
    0.09
    yers
    0.09
    .age
    0.09
     ages
    0.09
     atl
    0.09
     centuries
    0.09
    Activations Density 0.018%

    No Known Activations