© 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. 34029
    Prev
    Next
    INDEX
    Explanations

    exceeds expectations or what

    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
     nag
    -0.10
    æĢģ
    -0.10
     viewport
    -0.09
    管
    -0.09
    oya
    -0.09
    /li
    -0.09
    øy
    -0.09
    ood
    -0.09
     hic
    -0.09
     irresistible
    -0.09
    POSITIVE LOGITS
     sleeper
    0.09
    angan
    0.09
     surpr
    0.09
     surprise
    0.09
     fid
    0.09
    pics
    0.09
     dr
    0.09
     masc
    0.08
    wow
    0.08
    clusions
    0.08
    Activations Density 0.001%

    No Known Activations