© 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. 113042
    Prev
    Next
    INDEX
    Explanations

    article related 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
     DVDs
    -0.13
     recordings
    -0.12
     books
    -0.11
     recorded
    -0.11
     Recorded
    -0.11
     tapes
    -0.11
     CDs
    -0.11
     manuals
    -0.11
     Documentation
    -0.11
     records
    -0.10
    POSITIVE LOGITS
     article
    0.56
     articles
    0.44
    article
    0.42
    -article
    0.39
     Article
    0.39
    /article
    0.37
    æĸĩç«ł
    0.36
    Article
    0.35
    _article
    0.35
     ARTICLE
    0.33
    Activations Density 0.698%

    No Known Activations