© 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. 50854
    Prev
    Next
    INDEX
    Explanations

    son of, von, II, de

    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
    cox
    -0.09
    /mod
    -0.09
     Parade
    -0.09
    /main
    -0.09
     eid
    -0.09
     vista
    -0.09
    >manual
    -0.09
     Nations
    -0.09
    ToLeft
    -0.09
    Summer
    -0.08
    POSITIVE LOGITS
     of
    0.14
    -of
    0.14
    -the
    0.13
    _the
    0.12
    _of
    0.12
     son
    0.11
     von
    0.11
     II
    0.11
     dei
    0.10
     dalle
    0.10
    Activations Density 0.266%

    No Known Activations