© 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. 3553
    Prev
    Next
    INDEX
    Explanations

    age or year

    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
    aldi
    -0.09
     '~
    -0.09
     untranslated
    -0.09
     "~
    -0.09
    ongo
    -0.09
     Dund
    -0.09
     Abbott
    -0.09
    JA
    -0.09
    _about
    -0.08
    almost
    -0.08
    POSITIVE LOGITS
     officially
    0.10
     eligible
    0.10
    gers
    0.10
    owe
    0.09
     Accept
    0.09
     redistributed
    0.09
     accept
    0.09
     okay
    0.09
     accepting
    0.09
     interim
    0.09
    Activations Density 0.019%

    No Known Activations