© 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. 25231
    Prev
    Next
    INDEX
    Explanations

    sleep and unconsciousness

    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
     overst
    -0.11
     opposite
    -0.09
     formal
    -0.09
     informal
    -0.09
    uzzy
    -0.09
     horizontal
    -0.09
     Vert
    -0.09
     fatigue
    -0.08
     trap
    -0.08
     Caption
    -0.08
    POSITIVE LOGITS
     unconscious
    0.20
     dreaming
    0.19
     unknow
    0.18
     subconscious
    0.18
     REM
    0.14
     unaware
    0.14
     sleeper
    0.14
     unwitting
    0.14
     dream
    0.14
     dreamed
    0.14
    Activations Density 0.063%

    No Known Activations