© 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. 88905
    Prev
    Next
    INDEX
    Explanations

    aware/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
    orary
    -0.10
    DIV
    -0.10
    bia
    -0.09
     bou
    -0.09
     Juni
    -0.09
    akt
    -0.09
     diam
    -0.09
     uns
    -0.09
     Pix
    -0.09
    authorization
    -0.09
    POSITIVE LOGITS
    aware
    0.20
     awareness
    0.20
     Awareness
    0.20
    Aware
    0.18
     aware
    0.18
    -aware
    0.17
     Aware
    0.17
     consciousness
    0.14
     awake
    0.11
     conscious
    0.10
    Activations Density 0.092%

    No Known Activations