© 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. 92608
    Prev
    Next
    INDEX
    Explanations

    Sebelius, Seidman, Seam, Segnitz, Seiko, Se sh

    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
     proced
    -0.09
     bif
    -0.08
     ETA
    -0.08
     incest
    -0.07
     heed
    -0.07
     Least
    -0.07
     deceit
    -0.07
     sui
    -0.07
     neat
    -0.07
     exert
    -0.07
    POSITIVE LOGITS
    (SE
    0.16
    /se
    0.14
    (se
    0.12
    -se
    0.11
     se
    0.10
    -Se
    0.10
     Se
    0.10
    chts
    0.10
    bdd
    0.09
    :''
    0.09
    Activations Density 0.585%

    No Known Activations