© 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. 13923
    Prev
    Next
    INDEX
    Explanations

    time periods

    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
     before
    -0.13
    before
    -0.10
    Before
    -0.08
     Rus
    -0.08
    trained
    -0.08
     Before
    -0.08
     BEFORE
    -0.08
     trained
    -0.08
    bbox
    -0.07
    	before
    -0.07
    POSITIVE LOGITS
     delay
    0.16
     pause
    0.14
     longer
    0.13
     gest
    0.12
     spent
    0.12
     standoff
    0.12
     hiatus
    0.11
     Delay
    0.11
    spent
    0.11
     wherein
    0.11
    Activations Density 0.021%

    No Known Activations