© 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. 18757
    Prev
    Next
    INDEX
    Explanations

    building parts and locations

    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
    aira
    -0.10
     Rack
    -0.09
     rack
    -0.09
    zel
    -0.09
     Canon
    -0.08
    ervo
    -0.08
     Wik
    -0.08
    respect
    -0.08
    depends
    -0.08
    ourg
    -0.08
    POSITIVE LOGITS
     downstairs
    0.20
     upstairs
    0.17
     downtown
    0.15
    /windows
    0.12
     inside
    0.11
     around
    0.11
     everywhere
    0.11
     Karl
    0.11
    /window
    0.10
     onsite
    0.10
    Activations Density 0.840%

    No Known Activations