© 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. 18616
    Prev
    Next
    INDEX
    Explanations

    infamous controversial events

    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
    unan
    -0.08
    anim
    -0.08
     Maher
    -0.08
     discreet
    -0.08
     totalement
    -0.08
    kok
    -0.07
    Mixed
    -0.07
    wer
    -0.07
     Monthly
    -0.07
     khi
    -0.07
    POSITIVE LOGITS
     famously
    0.32
     notoriously
    0.15
     supposedly
    0.15
     titular
    0.13
     allegedly
    0.13
     infamous
    0.13
     famous
    0.13
     ostensibly
    0.12
     controversial
    0.11
     Wikipedia
    0.10
    Activations Density 3.979%

    No Known Activations