© 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. 45963
    Prev
    Next
    INDEX
    Explanations

    .svg file, consortium, active

    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
    sie
    -0.09
     Cutting
    -0.09
     tipping
    -0.09
     sensible
    -0.09
     conc
    -0.09
     Concord
    -0.08
     inspiring
    -0.08
    hev
    -0.08
     t
    -0.08
     DM
    -0.08
    POSITIVE LOGITS
    amos
    0.09
     Holl
    0.09
    andi
    0.09
    normally
    0.09
    arch
    0.09
     chromosomes
    0.09
     Reflex
    0.09
    crawl
    0.09
     partic
    0.08
    -flex
    0.08
    Activations Density 0.001%

    No Known Activations