© 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. 87860
    Prev
    Next
    INDEX
    Explanations

    are CAPS aligned

    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
     weren
    -0.09
     Civic
    -0.08
    ika
    -0.08
     inevitable
    -0.08
     aren
    -0.08
     Vive
    -0.08
     infamous
    -0.08
     underrated
    -0.08
    ayette
    -0.08
    oad
    -0.08
    POSITIVE LOGITS
     accounted
    0.21
     either
    0.19
    Either
    0.16
     EITHER
    0.15
     Either
    0.15
     covered
    0.15
    either
    0.14
     carefully
    0.13
     interconnected
    0.12
     Covered
    0.12
    Activations Density 0.176%

    No Known Activations