© 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. 50766
    Prev
    Next
    INDEX
    Explanations

    my .uk domain

    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
     upfront
    -0.13
    bib
    -0.10
     appreciated
    -0.10
     Bren
    -0.10
     customized
    -0.10
     careg
    -0.10
     DIY
    -0.10
     Weinstein
    -0.09
    oday
    -0.09
    —or
    -0.09
    POSITIVE LOGITS
     unins
    0.11
     lazy
    0.11
     mates
    0.11
     insure
    0.11
     complet
    0.10
    Manchester
    0.10
     mate
    0.10
     (£
    0.10
     utilise
    0.10
     £
    0.10
    Activations Density 0.006%

    No Known Activations