© 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. 117242
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Platt
    -0.11
     Aub
    -0.10
     Williamson
    -0.10
    ESA
    -0.10
     uncomp
    -0.09
     relegated
    -0.09
     monot
    -0.09
     personnel
    -0.09
    /current
    -0.09
    /work
    -0.09
    POSITIVE LOGITS
     kir
    0.09
    öt
    0.09
     lei
    0.09
    iset
    0.09
    oru
    0.08
    istas
    0.08
     Editors
    0.08
    kek
    0.08
     boom
    0.08
    %c
    0.08
    Activations Density 0.000%

    No Known Activations