© 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. 46117
    Prev
    Next
    INDEX
    Explanations

    header guards and file paths

    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
     irres
    -0.08
     theat
    -0.08
    è¯Ŀ
    -0.08
    .tk
    -0.08
     aj
    -0.08
     feast
    -0.08
    CRT
    -0.07
     Odd
    -0.07
    ql
    -0.07
    odd
    -0.07
    POSITIVE LOGITS
     trimest
    0.11
     Replacement
    0.10
     Watkins
    0.10
     cand
    0.10
    .heading
    0.10
    DBG
    0.10
    kel
    0.09
     Garten
    0.09
     heading
    0.09
     convo
    0.09
    Activations Density 0.003%

    No Known Activations