© 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. 8039
    Prev
    Next
    INDEX
    Explanations

    Choose, use, install, find, personalize

    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
    orate
    -0.09
     inst
    -0.08
     actually
    -0.08
     Ramirez
    -0.08
    rawl
    -0.08
     very
    -0.08
     prolifer
    -0.07
    assume
    -0.07
    /stretch
    -0.07
     ig
    -0.07
    POSITIVE LOGITS
     yours
    0.13
     anytime
    0.12
    ting
    0.11
     anywhere
    0.11
     alone
    0.11
    oola
    0.11
    -any
    0.10
     whichever
    0.10
    able
    0.10
     dazu
    0.10
    Activations Density 0.136%

    No Known Activations