© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18634
    Prev
    Next
    INDEX
    Explanations

    article/articles

    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
    Negative Logits
    iful
    -0.11
    tings
    -0.10
    ota
    -0.09
    à¹Į
    -0.09
    ous
    -0.09
    rael
    -0.09
    RAR
    -0.09
     Dop
    -0.08
    nut
    -0.08
    nier
    -0.08
    POSITIVE LOGITS
     articles
    0.14
    .Article
    0.14
    /article
    0.14
    Articles
    0.14
     Articles
    0.13
     headline
    0.13
    ulate
    0.13
     Article
    0.12
    ulation
    0.12
     article
    0.12
    Activations Density 0.038%

    No Known Activations