© 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. 24968
    Prev
    Next
    INDEX
    Explanations

    Av followed by common suffixes

    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
    vents
    -0.11
    accordion
    -0.10
    ToArray
    -0.10
     Clover
    -0.10
     whipping
    -0.10
    ########
    -0.09
    /array
    -0.09
    lep
    -0.08
    lez
    -0.08
    Lov
    -0.08
    POSITIVE LOGITS
    uning
    0.10
    ignon
    0.09
     borderline
    0.09
     Tower
    0.09
     tower
    0.09
    maid
    0.09
    %%%%%%%%
    0.09
     pole
    0.09
    ellar
    0.09
    END
    0.09
    Activations Density 0.059%

    No Known Activations