© 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. 27457
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation following words

    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
     advertisement
    -0.13
     google
    -0.12
     advertisements
    -0.12
     adverts
    -0.12
     matlab
    -0.11
     goog
    -0.11
     youtube
    -0.11
     ought
    -0.10
     wikipedia
    -0.10
    Advertisements
    -0.10
    POSITIVE LOGITS
     staffers
    0.16
     longtime
    0.14
     staffer
    0.13
     EVP
    0.13
     reportedly
    0.12
     ops
    0.11
     ÂŃ
    0.11
     ecommerce
    0.11
    .—
    0.11
     merch
    0.11
    Activations Density 2.173%

    No Known Activations