© 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. 92662
    Prev
    Next
    INDEX
    Explanations

    fetal development and health

    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
     foyer
    -0.11
    wand
    -0.09
    -media
    -0.09
    alli
    -0.09
     energies
    -0.08
     Pon
    -0.08
    -energy
    -0.08
    alic
    -0.08
    ceeded
    -0.08
     Vel
    -0.08
    POSITIVE LOGITS
    agr
    0.12
     Neil
    0.11
    ufs
    0.10
    forma
    0.10
    ecn
    0.10
    Neil
    0.10
    áln
    0.10
     state
    0.10
     Trader
    0.09
     cot
    0.09
    Activations Density 0.005%

    No Known Activations