© 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. 46162
    Prev
    Next
    INDEX
    Explanations

    drug contamination purity batches

    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
     ephem
    -0.10
     rub
    -0.10
     disag
    -0.09
    Temporary
    -0.09
     transient
    -0.09
     temporary
    -0.09
     Provision
    -0.09
    fram
    -0.09
     Canc
    -0.09
    ivy
    -0.09
    POSITIVE LOGITS
     contamination
    0.24
     purity
    0.23
     contaminants
    0.22
     adul
    0.21
     contaminated
    0.20
     contamin
    0.18
     tainted
    0.17
     batches
    0.16
     batch
    0.15
     imp
    0.14
    Activations Density 0.380%

    No Known Activations