© 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. 92476
    Prev
    Next
    INDEX
    Explanations

    collections of works

    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
    apat
    -0.10
    coc
    -0.10
     Vern
    -0.10
    ernet
    -0.09
    alta
    -0.09
    .CopyTo
    -0.09
     vero
    -0.09
     flurry
    -0.09
     vern
    -0.09
     eman
    -0.08
    POSITIVE LOGITS
     consisting
    0.23
     containing
    0.22
     comprising
    0.19
     contains
    0.17
     consolid
    0.17
     consists
    0.16
     comprised
    0.16
     consist
    0.16
     includes
    0.16
     contain
    0.16
    Activations Density 1.294%

    No Known Activations