© 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. 32493
    Prev
    Next
    INDEX
    Explanations

    joy and pleasure

    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
     starving
    -0.12
     attractive
    -0.10
     appealing
    -0.10
     Needed
    -0.10
    ibal
    -0.10
    oden
    -0.10
     bored
    -0.10
    emie
    -0.10
    /stat
    -0.10
     Perception
    -0.10
    POSITIVE LOGITS
     pleasure
    0.18
     delight
    0.18
     enjoyment
    0.17
     delights
    0.15
     joy
    0.15
     watching
    0.14
     delighted
    0.14
     revel
    0.14
     derived
    0.14
     seeing
    0.13
    Activations Density 0.048%

    No Known Activations