© 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. 51000
    Prev
    Next
    INDEX
    Explanations

    name "Mark" followed by a surname

    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
    imi
    -0.10
     teg
    -0.10
    pires
    -0.10
     technically
    -0.10
     perc
    -0.10
    iaux
    -0.09
    erno
    -0.09
     bog
    -0.09
     undercover
    -0.09
    nage
    -0.08
    POSITIVE LOGITS
     appart
    0.10
     incons
    0.10
     Willis
    0.10
    edd
    0.09
     Strand
    0.09
    .parametrize
    0.09
    atis
    0.09
    hot
    0.09
    eds
    0.09
    acom
    0.09
    Activations Density 0.005%

    No Known Activations