© 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. 117478
    Prev
    Next
    INDEX
    Explanations

    work and home stress

    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
     Sovere
    -0.10
    (TR
    -0.09
     maneuvers
    -0.09
     BR
    -0.08
     Lionel
    -0.08
     honeymoon
    -0.08
     na
    -0.08
     naive
    -0.08
     dro
    -0.08
    Preference
    -0.08
    POSITIVE LOGITS
     worries
    0.27
     responsibilities
    0.24
     stresses
    0.23
     stressful
    0.22
     stress
    0.22
     obligations
    0.21
     worry
    0.20
     distractions
    0.20
     Stress
    0.20
     unfinished
    0.20
    Activations Density 0.055%

    No Known Activations