© 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. 7991
    Prev
    Next
    INDEX
    Explanations

    fusion inhibitors, AIDS vaccine, International AIDS

    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
    Not in Any Lists

    No Comments

    Negative Logits
     uphol
    -0.10
     gord
    -0.10
     upholstery
    -0.10
     disg
    -0.10
    erb
    -0.09
     Georg
    -0.09
     mamma
    -0.09
     dec
    -0.09
     mats
    -0.09
     stool
    -0.09
    POSITIVE LOGITS
     latex
    0.13
     condom
    0.12
     Lat
    0.12
     Sid
    0.11
     circumcision
    0.11
     condoms
    0.10
    Lat
    0.10
     sidew
    0.10
     latency
    0.10
    .band
    0.10
    Activations Density 0.050%

    No Known Activations