© 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. 33971
    Prev
    Next
    INDEX
    Explanations

    greeting welcomes

    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
    /list
    -0.09
     TW
    -0.09
    aban
    -0.09
     compelling
    -0.08
     Tik
    -0.08
     Gal
    -0.08
     earnest
    -0.08
     Greenwood
    -0.08
     persever
    -0.08
     cert
    -0.08
    POSITIVE LOGITS
     greeting
    0.42
     greetings
    0.38
     greet
    0.37
     greeted
    0.35
     welcome
    0.30
     welcoming
    0.29
     welcomed
    0.28
     welcomes
    0.28
     Welcome
    0.27
    Greetings
    0.25
    Activations Density 0.082%

    No Known Activations