© 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. 117505
    Prev
    Next
    INDEX
    Explanations

    pleasure, joy, and pain sensations

    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
     Bacon
    -0.10
     disproportion
    -0.09
     ejac
    -0.09
    unch
    -0.09
     Cleanup
    -0.09
    asco
    -0.09
     inse
    -0.09
    perse
    -0.09
    UNCH
    -0.09
     circum
    -0.09
    POSITIVE LOGITS
     sensations
    0.19
     sensation
    0.15
     pain
    0.14
     overload
    0.13
     inflicted
    0.13
     pleasures
    0.13
     torture
    0.13
     courtesy
    0.13
     ache
    0.12
    pain
    0.12
    Activations Density 0.005%

    No Known Activations