© 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. 46336
    Prev
    Next
    INDEX
    Explanations

    bodily chemical reactions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     (~
    -0.13
     intimately
    -0.12
     maximal
    -0.11
     nicely
    -0.11
     ~
    -0.10
     elucid
    -0.10
     transient
    -0.10
     milieu
    -0.10
     conferred
    -0.09
     exquisite
    -0.09
    POSITIVE LOGITS
     chemicals
    0.17
     dormant
    0.15
     reactionary
    0.14
     reacts
    0.14
     chemical
    0.14
     receptions
    0.14
     bodily
    0.13
     aide
    0.13
     medical
    0.13
     reacting
    0.13
    Activations Density 0.261%

    No Known Activations