© 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. 92580
    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
    ATO
    -0.11
    cosa
    -0.11
    mux
    -0.10
    idian
    -0.10
     Shiv
    -0.10
     Dixon
    -0.10
     trench
    -0.10
     mutable
    -0.09
    mut
    -0.09
    unicorn
    -0.09
    POSITIVE LOGITS
     incoming
    0.08
     Lore
    0.08
    âĢij
    0.08
     CPS
    0.08
     aerial
    0.08
     scream
    0.08
    iser
    0.08
     IE
    0.08
     visual
    0.07
     Visual
    0.07
    Activations Density 0.000%

    No Known Activations