© 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. 17692
    Prev
    Next
    INDEX
    Explanations

    stress and relaxation

    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
     embarrassed
    -0.10
     embarrassing
    -0.10
     deaf
    -0.09
     blinded
    -0.09
     disgrace
    -0.09
     blindness
    -0.09
     embarrass
    -0.09
    cir
    -0.09
     decency
    -0.09
     lust
    -0.09
    POSITIVE LOGITS
     stress
    0.74
     Stress
    0.71
    stress
    0.63
     stressful
    0.60
     stressed
    0.57
     stresses
    0.55
     relaxation
    0.50
     stressing
    0.47
     Relax
    0.46
     relaxing
    0.44
    Activations Density 0.750%

    No Known Activations