© 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. 46147
    Prev
    Next
    INDEX
    Explanations

    coconut oil, fatty acids

    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
     Petr
    -0.12
     IBM
    -0.12
     tob
    -0.12
    IBM
    -0.12
    xor
    -0.11
     quartz
    -0.11
     Czech
    -0.11
     Benn
    -0.11
    èį
    -0.10
     underwater
    -0.10
    POSITIVE LOGITS
     coconut
    0.31
     Coconut
    0.30
     cocos
    0.17
    conut
    0.16
     tropical
    0.15
     Coco
    0.15
     fatty
    0.14
     cooking
    0.13
    ocos
    0.13
     palm
    0.13
    Activations Density 0.170%

    No Known Activations