© 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. 27827
    Prev
    Next
    INDEX
    Explanations

    sentient and conscious beings

    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
     prow
    -0.10
     reels
    -0.09
     weed
    -0.09
    Unchecked
    -0.09
     tallest
    -0.09
     embracing
    -0.09
     sweaty
    -0.09
     Americas
    -0.09
     dirty
    -0.09
     embrace
    -0.09
    POSITIVE LOGITS
     sentient
    0.29
     consciousness
    0.21
     Conscious
    0.20
     anthrop
    0.19
     responsiveness
    0.19
     conscious
    0.19
     humanoid
    0.17
     intelig
    0.17
     intelligent
    0.17
     intelligence
    0.17
    Activations Density 0.181%

    No Known Activations