© 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. 111559
    Prev
    Next
    INDEX
    Explanations

    dates and discounts

    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
    filt
    -0.11
    aho
    -0.10
    .tm
    -0.10
    jes
    -0.10
     amalg
    -0.10
    =sub
    -0.09
     Signature
    -0.09
    lobby
    -0.09
    -heading
    -0.09
     nor
    -0.09
    POSITIVE LOGITS
     Witt
    0.09
    plx
    0.09
    tro
    0.09
     Burke
    0.09
     scarcity
    0.09
     wag
    0.08
     carts
    0.08
     shortage
    0.08
    ungs
    0.08
    elle
    0.08
    Activations Density 0.002%

    No Known Activations