© 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. 117264
    Prev
    Next
    INDEX
    Explanations

    classic or seminal works

    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
     busiest
    -0.10
    /team
    -0.10
     specialization
    -0.10
     Bai
    -0.09
    married
    -0.09
    —who
    -0.09
     Samp
    -0.09
     Activities
    -0.09
     Websites
    -0.09
     Bounty
    -0.09
    POSITIVE LOGITS
     masterpiece
    0.26
     cult
    0.17
     groundbreaking
    0.16
     seminal
    0.15
     contains
    0.15
     premiered
    0.15
     landmark
    0.14
     banned
    0.14
     unread
    0.14
     containing
    0.14
    Activations Density 0.650%

    No Known Activations