© 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. 8156
    Prev
    Next
    INDEX
    Explanations

    visual reaction or query

    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
     Hearing
    -0.09
    æľ
    -0.09
     Beacon
    -0.09
     Journey
    -0.09
     licking
    -0.09
     rallies
    -0.09
    hear
    -0.09
     fluct
    -0.08
     lear
    -0.08
     Mum
    -0.08
    POSITIVE LOGITS
     cosy
    0.10
    unread
    0.10
     notifying
    0.09
     unexpectedly
    0.09
     containing
    0.09
     informing
    0.09
     Lara
    0.09
     sext
    0.09
     itself
    0.09
     Wie
    0.09
    Activations Density 0.001%

    No Known Activations