© 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. 92450
    Prev
    Next
    INDEX
    Explanations

    reporting opinions and observations

    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
     yourselves
    -0.10
     randomly
    -0.08
     Him
    -0.08
     adjunct
    -0.08
     Charl
    -0.08
     Nun
    -0.08
    Exact
    -0.08
    è¡
    -0.08
    iance
    -0.08
     adj
    -0.08
    POSITIVE LOGITS
     unnamed
    0.11
     extensively
    0.11
    cribes
    0.10
     readers
    0.10
     "["
    0.10
     riff
    0.09
     Morrow
    0.09
    istra
    0.09
     several
    0.09
     sounding
    0.09
    Activations Density 0.664%

    No Known Activations