© 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. 25129
    Prev
    Next
    INDEX
    Explanations

    before

    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
    cum
    -0.11
     recip
    -0.10
    oi
    -0.10
     Barton
    -0.10
    rans
    -0.10
    ono
    -0.09
    olas
    -0.09
    weise
    -0.09
    iff
    -0.09
    /helpers
    -0.09
    POSITIVE LOGITS
     bedtime
    0.12
     sunrise
    0.11
     eyes
    0.11
     Eyes
    0.11
    awn
    0.11
     dawn
    0.11
     Geb
    0.10
     noon
    0.10
    emin
    0.10
    mentioned
    0.10
    Activations Density 0.174%

    No Known Activations