© 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. 13972
    Prev
    Next
    INDEX
    Explanations

    body following supra, each atom, intern by rule, this post

    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
     microscopic
    -0.09
     dirig
    -0.09
     somehow
    -0.08
     secre
    -0.08
     harb
    -0.08
     bait
    -0.08
     matchmaking
    -0.08
     increment
    -0.08
     harassment
    -0.08
     Carm
    -0.08
    POSITIVE LOGITS
     fell
    0.12
     collapse
    0.12
     collapses
    0.11
    Splash
    0.11
     screamed
    0.11
     fall
    0.11
     Splash
    0.11
    collapse
    0.10
     irresistible
    0.10
     instantly
    0.10
    Activations Density 0.044%

    No Known Activations