© 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. 8155
    Prev
    Next
    INDEX
    Explanations

    canned goods or cans

    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
     ble
    -0.11
     bib
    -0.10
     Levy
    -0.10
     ornament
    -0.09
    ypsum
    -0.09
     anatom
    -0.09
    .cross
    -0.09
    .bundle
    -0.09
     cred
    -0.09
     steering
    -0.09
    POSITIVE LOGITS
     cans
    0.32
     canned
    0.29
     tin
    0.23
     Tin
    0.19
     tuna
    0.18
    tin
    0.17
     cann
    0.17
     Cann
    0.17
     Spam
    0.16
     Campbell
    0.14
    Activations Density 0.165%

    No Known Activations