© 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. 50902
    Prev
    Next
    INDEX
    Explanations

    physical components or spaces

    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
     WHILE
    -0.12
     whilst
    -0.11
    ARP
    -0.11
    until
    -0.11
    -decoration
    -0.10
     onwards
    -0.10
    emos
    -0.10
     simultaneously
    -0.10
     until
    -0.10
    while
    -0.10
    POSITIVE LOGITS
     capable
    0.12
     suitable
    0.11
     capability
    0.11
     for
    0.10
     allowing
    0.10
     surrounded
    0.09
     anda
    0.09
     allows
    0.09
    Allows
    0.09
     Boyle
    0.08
    Activations Density 0.292%

    No Known Activations