© 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. 18734
    Prev
    Next
    INDEX
    Explanations

    expect to verb

    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
     unintended
    -0.09
     ensure
    -0.09
     promise
    -0.09
     unfore
    -0.09
    utra
    -0.09
     unexpected
    -0.09
    uti
    -0.09
    zan
    -0.09
     seek
    -0.09
     accept
    -0.09
    POSITIVE LOGITS
     hear
    0.18
     hearing
    0.17
     see
    0.16
     Hear
    0.15
     sees
    0.14
     hears
    0.14
     Hearing
    0.13
     seeing
    0.13
     heard
    0.13
     needing
    0.12
    Activations Density 0.026%

    No Known Activations