© 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. 117497
    Prev
    Next
    INDEX
    Explanations

    a or an followed by a word

    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
     separate
    -0.10
     primitives
    -0.10
     cac
    -0.10
     practiced
    -0.10
    çIJ
    -0.09
     directions
    -0.09
     outs
    -0.09
     stump
    -0.09
     constellation
    -0.09
     timeframe
    -0.09
    POSITIVE LOGITS
     rectangular
    0.11
     Cater
    0.10
     cater
    0.10
     Mend
    0.10
     amusement
    0.09
     newborn
    0.09
     nx
    0.09
    /an
    0.09
    suming
    0.09
     singly
    0.09
    Activations Density 1.577%

    No Known Activations