© 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. 117430
    Prev
    Next
    INDEX
    Explanations

    days, times, or locations

    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
    agar
    -0.10
     pon
    -0.10
    cher
    -0.09
    icone
    -0.09
     Handy
    -0.09
     Wilhelm
    -0.09
     Cher
    -0.09
     chrome
    -0.09
     Ruiz
    -0.09
    Vers
    -0.09
    POSITIVE LOGITS
    stead
    0.09
     Char
    0.09
    arda
    0.09
     ADC
    0.08
     IST
    0.08
     repeating
    0.08
     Burl
    0.08
    etc
    0.08
     bait
    0.08
    estion
    0.07
    Activations Density 0.049%

    No Known Activations