© 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. 92635
    Prev
    Next
    INDEX
    Explanations

    Folkestone and Hythe

    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
     Celtics
    -0.13
     Braz
    -0.12
     BSON
    -0.11
    Rio
    -0.11
     Salesforce
    -0.11
     Bordeaux
    -0.11
     Oracle
    -0.11
     Granite
    -0.11
     Cain
    -0.11
     Berkshire
    -0.11
    POSITIVE LOGITS
     γ
    0.15
     Surrey
    0.15
     Kerala
    0.14
     Kent
    0.14
     Îĵ
    0.13
     Joomla
    0.13
     Sussex
    0.13
    Kent
    0.13
     Brighton
    0.13
     Canterbury
    0.13
    Activations Density 3.180%

    No Known Activations