© 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. 8192
    Prev
    Next
    INDEX
    Explanations

    being an eager

    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
     Hopefully
    -0.09
     hopefully
    -0.08
     contrasts
    -0.07
     slowly
    -0.07
    ?action
    -0.06
     eventually
    -0.06
     finally
    -0.06
    Hopefully
    -0.06
     segmented
    -0.06
    rib
    -0.06
    POSITIVE LOGITS
     wanting
    0.21
    being
    0.18
     knowing
    0.18
     being
    0.18
     sensing
    0.18
     fearing
    0.17
     eager
    0.16
    Being
    0.16
     naturally
    0.16
     needing
    0.16
    Activations Density 0.091%

    No Known Activations