© 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. 33587
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and months

    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
    1
    -0.12
    01
    -0.12
    ¹
    -0.10
    aced
    -0.10
     reluctantly
    -0.09
     conscience
    -0.09
    0
    -0.09
    otte
    -0.09
    onia
    -0.09
    chia
    -0.09
    POSITIVE LOGITS
     third
    0.14
    ï¼Ķ
    0.12
    ï¼ĵ
    0.12
    ³
    0.12
     fourth
    0.12
    third
    0.11
     Third
    0.11
    3
    0.11
    4
    0.11
     March
    0.10
    Activations Density 0.376%

    No Known Activations