© 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. 92426
    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
    Negative Logits
     outright
    -0.11
     Perkins
    -0.09
    upa
    -0.09
     wrap
    -0.09
    wrap
    -0.09
     upfront
    -0.09
     Whip
    -0.08
     unw
    -0.08
     Jong
    -0.08
    Ĩ
    -0.08
    POSITIVE LOGITS
    ensing
    0.11
    /il
    0.11
     Lei
    0.10
    -UA
    0.10
     childs
    0.10
    stor
    0.10
     disillusion
    0.09
    hem
    0.09
    +xml
    0.09
    ABEL
    0.09
    Activations Density 0.000%

    No Known Activations