© 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. 34044
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and code syntax

    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
    979
    -0.13
    Nib
    -0.12
    inspect
    -0.12
     acab
    -0.12
     integ
    -0.12
    alleries
    -0.12
    heels
    -0.11
    efe
    -0.11
     Ends
    -0.11
    zimmer
    -0.11
    POSITIVE LOGITS
    ker
    0.11
     behind
    0.08
     mint
    0.08
     Singles
    0.08
     sext
    0.07
     neck
    0.07
    sb
    0.07
     singles
    0.07
     gag
    0.07
     throat
    0.07
    Activations Density 0.006%

    No Known Activations