© 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. 92582
    Prev
    Next
    INDEX
    Explanations

    graduation and commencement ceremonies

    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
     graduated
    -0.10
     graduates
    -0.09
     Crosby
    -0.08
     progressed
    -0.08
    ated
    -0.08
    _gradient
    -0.08
    bir
    -0.08
    /he
    -0.08
     Sylvia
    -0.07
     progressing
    -0.07
    POSITIVE LOGITS
     ceremonies
    0.21
     ceremony
    0.18
     Ceremony
    0.15
     Cer
    0.14
     Gifts
    0.12
     Gift
    0.12
     cer
    0.12
     rites
    0.12
     gift
    0.11
    /send
    0.11
    Activations Density 0.039%

    No Known Activations