© 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. 18479
    Prev
    Next
    INDEX
    Explanations

    books and desks

    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
    otto
    -0.09
    inned
    -0.09
     lien
    -0.09
    isman
    -0.08
    rored
    -0.08
     extras
    -0.08
     Posting
    -0.08
    ammo
    -0.08
    332
    -0.08
     Sac
    -0.08
    POSITIVE LOGITS
     books
    0.18
     textbooks
    0.16
     screens
    0.15
    -books
    0.14
     paperwork
    0.14
     crossword
    0.14
     desk
    0.14
     Books
    0.13
    books
    0.13
    Books
    0.13
    Activations Density 0.066%

    No Known Activations