© 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. 13887
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     zig
    -0.08
     sideways
    -0.08
     pom
    -0.08
    ses
    -0.08
    rita
    -0.08
    rud
    -0.08
    os
    -0.08
    ма
    -0.07
     electorate
    -0.07
     burger
    -0.07
    POSITIVE LOGITS
    angep
    0.11
     blows
    0.11
    elve
    0.11
    acad
    0.11
     Bart
    0.10
     Aires
    0.10
     empir
    0.10
     door
    0.10
     Alic
    0.10
     Impress
    0.10
    Activations Density 0.000%

    No Known Activations