© 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. 34079
    Prev
    Next
    INDEX
    Explanations

    uni prefixes

    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
     Kickstarter
    -0.10
     Hubb
    -0.10
    uum
    -0.09
     Woods
    -0.09
     Virgin
    -0.09
    asio
    -0.09
    uta
    -0.09
    ooke
    -0.08
    EF
    -0.08
     lean
    -0.08
    POSITIVE LOGITS
     Cro
    0.10
    iglia
    0.09
     cro
    0.09
    indow
    0.09
    chalk
    0.09
     Shawn
    0.09
     sucker
    0.09
     aud
    0.08
     facet
    0.08
     bureaucr
    0.08
    Activations Density 0.010%

    No Known Activations