© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15940
    Prev
    Next
    INDEX
    Explanations

    hormones and neurotransmitters

    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
     datab
    -0.11
     cvs
    -0.10
     sucess
    -0.09
     recap
    -0.09
     EW
    -0.09
     Petit
    -0.09
     acknow
    -0.09
     Nico
    -0.09
     iv
    -0.09
     mechanically
    -0.09
    POSITIVE LOGITS
     hormones
    0.36
     serotonin
    0.26
     dopamine
    0.25
     testosterone
    0.25
     hormone
    0.24
     neurotrans
    0.24
     adrenaline
    0.22
     cortisol
    0.21
     estrogen
    0.21
     chemicals
    0.19
    Activations Density 1.587%

    No Known Activations