© 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. 34222
    Prev
    Next
    INDEX
    Explanations

    reunion greetings

    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
     lur
    -0.11
    ~/
    -0.11
    uyo
    -0.11
     Vet
    -0.10
     INV
    -0.10
    stalk
    -0.10
    VK
    -0.10
     slack
    -0.10
    vet
    -0.10
     dynasty
    -0.10
    POSITIVE LOGITS
     reunion
    0.17
     reun
    0.15
     hug
    0.15
     greet
    0.13
     reunited
    0.13
     hugged
    0.13
     hugs
    0.13
     greeting
    0.11
     greeted
    0.11
     greetings
    0.10
    Activations Density 0.064%

    No Known Activations