© 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. 117573
    Prev
    Next
    INDEX
    Explanations

    Holy Ghost

    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
     refresh
    -0.14
     freshness
    -0.14
    Refreshing
    -0.14
     Fresh
    -0.13
     fresh
    -0.13
    fresh
    -0.13
    Fresh
    -0.13
     refreshing
    -0.12
     Fres
    -0.12
     fres
    -0.12
    POSITIVE LOGITS
    phia
    0.09
     aur
    0.08
     Improved
    0.08
     CMP
    0.08
    çı
    0.08
     CD
    0.08
    abal
    0.08
     aure
    0.08
    arse
    0.08
     enhanced
    0.08
    Activations Density 0.001%

    No Known Activations