© 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. 18559
    Prev
    Next
    INDEX
    Explanations

    website disclaimers or terms

    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
     websites
    -0.24
     website
    -0.23
     Websites
    -0.21
     Website
    -0.19
    Website
    -0.17
    website
    -0.17
    _website
    -0.16
     webpage
    -0.13
    ç½ij
    -0.12
     Ñģай
    -0.12
    POSITIVE LOGITS
     Trout
    0.12
    htdocs
    0.10
    .SQLite
    0.10
    .RequestMethod
    0.10
    asto
    0.10
     Rockets
    0.10
    leet
    0.10
    ено
    0.09
     Spir
    0.09
     cocktails
    0.09
    Activations Density 0.436%

    No Known Activations