© 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. 18732
    Prev
    Next
    INDEX
    Explanations

    educational methods and learning

    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
     Official
    -0.12
     Conj
    -0.12
     esc
    -0.12
     dating
    -0.11
    Official
    -0.11
     Girlfriend
    -0.11
     male
    -0.10
     solidity
    -0.10
     Vanity
    -0.10
     Playboy
    -0.10
    POSITIVE LOGITS
     learner
    0.24
     learners
    0.23
     classroom
    0.20
     educators
    0.19
     organizational
    0.19
     facilit
    0.19
     practitioner
    0.18
     leadership
    0.18
     Leadership
    0.18
     Teaching
    0.18
    Activations Density 3.409%

    No Known Activations