© 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. 117323
    Prev
    Next
    INDEX
    Explanations

    shop or store

    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
    abol
    -0.10
     Hospitals
    -0.10
     Resorts
    -0.10
     Roads
    -0.10
    zon
    -0.10
    iez
    -0.09
     Organisation
    -0.09
     mature
    -0.09
     Schools
    -0.09
    /global
    -0.09
    POSITIVE LOGITS
     storefront
    0.19
     owner
    0.18
     owners
    0.16
     specializing
    0.16
    /store
    0.16
    -owner
    0.15
     downtown
    0.14
     proprietor
    0.14
     store
    0.14
    owner
    0.14
    Activations Density 0.189%

    No Known Activations