© 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. 3465
    Prev
    Next
    INDEX
    Explanations

    status updates

    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
     divor
    -0.12
    bor
    -0.11
    erot
    -0.11
     sled
    -0.11
     oltre
    -0.10
    ypse
    -0.10
    pac
    -0.10
    mund
    -0.10
     Brow
    -0.10
     kiss
    -0.10
    POSITIVE LOGITS
     ongoing
    0.20
     pending
    0.20
     awaiting
    0.17
     imminent
    0.17
     periodically
    0.17
     waiting
    0.17
     impending
    0.16
     simmer
    0.16
     ready
    0.15
    ongo
    0.15
    Activations Density 0.624%

    No Known Activations