© 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. 48912
    Prev
    Next
    INDEX
    Explanations

    when stressed or upset

    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
     civilian
    -0.10
    zem
    -0.10
    ince
    -0.10
    unread
    -0.09
     elig
    -0.09
    jah
    -0.09
     ply
    -0.09
     Glover
    -0.09
    447
    -0.09
    nah
    -0.09
    POSITIVE LOGITS
     stressed
    0.16
     after
    0.14
     stressful
    0.14
     stress
    0.14
     Stress
    0.14
     boredom
    0.13
     upset
    0.12
     stresses
    0.12
     holidays
    0.11
     emotional
    0.11
    Activations Density 0.049%

    No Known Activations