© 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. 87684
    Prev
    Next
    INDEX
    Explanations

    introducing new concepts

    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
     algún
    -0.12
     somehow
    -0.11
     alguna
    -0.11
     Someone
    -0.11
     SOME
    -0.11
     someone
    -0.11
     any
    -0.11
     Somebody
    -0.11
    Someone
    -0.11
     somebody
    -0.10
    POSITIVE LOGITS
     two
    0.18
     another
    0.17
    another
    0.14
    two
    0.13
     three
    0.13
    three
    0.11
     “
    0.10
     an
    0.10
    两
    0.10
    Two
    0.10
    Activations Density 1.815%

    No Known Activations