© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 4081
    Prev
    Next
    INDEX
    Explanations

    number of years or ordinal numbers

    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
    amp
    -0.11
    nd
    -0.10
    s
    -0.10
    FA
    -0.09
    nbsp
    -0.09
     differing
    -0.09
    lt
    -0.09
    oba
    -0.09
    HERE
    -0.09
    IC
    -0.09
    POSITIVE LOGITS
    fold
    0.33
    eenth
    0.27
    teenth
    0.22
    ième
    0.20
    teen
    0.20
    -four
    0.19
    -six
    0.19
    -five
    0.18
    een
    0.18
    veh
    0.17
    Activations Density 0.330%

    No Known Activations