© 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. 90310
    Prev
    Next
    INDEX
    Explanations

    breathing exercises

    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
     covert
    -0.12
     schem
    -0.12
     cram
    -0.11
     organising
    -0.11
     prestige
    -0.11
    cock
    -0.10
     partial
    -0.10
     stealth
    -0.10
     punish
    -0.10
     Cock
    -0.10
    POSITIVE LOGITS
     breathing
    0.31
     breathe
    0.28
     breath
    0.22
     breathed
    0.22
     inh
    0.21
     Breath
    0.21
     mindfulness
    0.21
     Bre
    0.19
     meditation
    0.19
    -bre
    0.18
    Activations Density 0.014%

    No Known Activations