© 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. 34206
    Prev
    Next
    INDEX
    Explanations

    household appliances and tasks

    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
     financier
    -0.09
    lian
    -0.09
     Administrative
    -0.08
     occupational
    -0.08
    wg
    -0.08
     Kurt
    -0.08
    rego
    -0.08
     Bowman
    -0.08
     cig
    -0.08
    orian
    -0.08
    POSITIVE LOGITS
     performed
    0.12
     boy
    0.11
    ster
    0.11
    enstein
    0.11
    /service
    0.11
    boy
    0.10
     whistle
    0.10
     done
    0.10
    men
    0.10
     assignments
    0.10
    Activations Density 0.007%

    No Known Activations