© 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. 87670
    Prev
    Next
    INDEX
    Explanations

    communication and information

    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
     traps
    -0.10
     asym
    -0.09
     Joe
    -0.09
    indr
    -0.09
     tortured
    -0.09
    scal
    -0.09
     divorced
    -0.09
    upt
    -0.08
    vern
    -0.08
     churn
    -0.08
    POSITIVE LOGITS
     Communication
    0.18
     communication
    0.18
    Communication
    0.16
    communication
    0.16
     communicating
    0.15
     communications
    0.15
     Communic
    0.15
     tele
    0.14
     entertainment
    0.14
     Entertainment
    0.14
    Activations Density 0.231%

    No Known Activations