© 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. 46116
    Prev
    Next
    INDEX
    Explanations

    when + condition/situation

    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
     Indexed
    -0.11
     Bere
    -0.08
    -born
    -0.08
     unit
    -0.08
     åº
    -0.08
     Coh
    -0.08
     Berkshire
    -0.08
     Killed
    -0.08
     pari
    -0.08
    enge
    -0.08
    POSITIVE LOGITS
     dealing
    0.16
     faced
    0.12
     there
    0.12
     accompanied
    0.11
     constantly
    0.11
     surrounded
    0.11
     outnumber
    0.11
     half
    0.11
     staring
    0.11
     teamed
    0.11
    Activations Density 0.073%

    No Known Activations