© 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. 8227
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
     selfies
    -0.12
     whitelist
    -0.11
     Pawn
    -0.10
     Dumpster
    -0.10
     Shift
    -0.09
     Slut
    -0.09
    .fm
    -0.09
     selfie
    -0.09
     Hover
    -0.09
     Batch
    -0.09
    POSITIVE LOGITS
    -Sah
    0.09
     mur
    0.09
     enlight
    0.09
     served
    0.09
     inward
    0.08
     deb
    0.08
     Rem
    0.08
     thereafter
    0.08
    atori
    0.08
     overst
    0.08
    Activations Density 0.014%

    No Known Activations