© 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. 117355
    Prev
    Next
    INDEX
    Explanations

    to simplify

    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
    anker
    -0.11
    baugh
    -0.09
     maiden
    -0.09
    tle
    -0.08
     singles
    -0.08
     Maiden
    -0.08
    hots
    -0.08
    omb
    -0.08
     commerce
    -0.08
     unins
    -0.08
    POSITIVE LOGITS
     panc
    0.12
     btw
    0.09
    pan
    0.09
    olley
    0.09
    .Net
    0.09
    kok
    0.09
    ças
    0.09
    SENT
    0.09
     hann
    0.09
     Panc
    0.09
    Activations Density 0.002%

    No Known Activations