© 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. 92658
    Prev
    Next
    INDEX
    Explanations

    relax, unwind, stress, cool, care

    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
    wid
    -0.13
    ulp
    -0.12
    lesi
    -0.11
    ardy
    -0.11
     Cond
    -0.11
     Handy
    -0.11
     inde
    -0.11
    COND
    -0.11
     awakening
    -0.11
    UIS
    -0.10
    POSITIVE LOGITS
     relax
    0.17
     relaxation
    0.16
     stress
    0.14
     unwind
    0.14
     Relax
    0.13
     relaxing
    0.12
     Stress
    0.12
     amidst
    0.11
     decom
    0.11
     after
    0.10
    Activations Density 0.023%

    No Known Activations