© 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. 17266
    Prev
    Next
    INDEX
    Explanations

    consciousness and awareness

    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
    elder
    -0.11
    elda
    -0.11
    ibold
    -0.10
    ãĤ«
    -0.10
    MIT
    -0.10
    bia
    -0.10
    ANTA
    -0.10
    -fin
    -0.10
     Fountain
    -0.10
    ANTE
    -0.09
    POSITIVE LOGITS
    -ra
    0.13
     bog
    0.12
     abl
    0.12
     awareness
    0.11
     raising
    0.11
    es
    0.11
    illet
    0.10
    Aware
    0.10
     Awareness
    0.10
     effort
    0.10
    Activations Density 0.029%

    No Known Activations