© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49679
    Prev
    Next
    INDEX
    Explanations

    stress and cortisol levels

    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
     humming
    -0.09
     muscular
    -0.09
     spontaneously
    -0.09
     subtotal
    -0.08
     rare
    -0.08
     Rare
    -0.08
     loosen
    -0.08
     Wig
    -0.08
     Reynolds
    -0.08
    -render
    -0.08
    POSITIVE LOGITS
     cortisol
    0.34
     Cort
    0.29
     stress
    0.26
     Stress
    0.25
    stress
    0.20
     cort
    0.19
     stressed
    0.19
     elevated
    0.18
     Elevated
    0.18
     levels
    0.15
    Activations Density 0.517%

    No Known Activations