© 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. 25178
    Prev
    Next
    INDEX
    Explanations

    communicating and communication

    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
     revived
    -0.09
     fitted
    -0.08
    als
    -0.08
     newborn
    -0.08
    ков
    -0.08
     fals
    -0.08
     umbrella
    -0.08
    uraa
    -0.07
    asse
    -0.07
    pone
    -0.07
    POSITIVE LOGITS
     communicated
    0.13
    communic
    0.12
     communicate
    0.12
     comunic
    0.12
     Communic
    0.11
     communicates
    0.11
     communicating
    0.11
    communication
    0.11
    tron
    0.10
     Communication
    0.10
    Activations Density 0.003%

    No Known Activations