© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46495
    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
    Not in Any Lists

    No Comments

    Negative Logits
    auc
    -0.11
     Rudd
    -0.11
     Sharp
    -0.10
     unp
    -0.10
    aviors
    -0.09
     gul
    -0.09
     commuting
    -0.09
     lul
    -0.09
     adjoining
    -0.09
    ="-
    -0.09
    POSITIVE LOGITS
    ument
    0.09
     punch
    0.09
     ale
    0.09
     wholesome
    0.09
    anten
    0.08
    erca
    0.08
    paged
    0.08
     fung
    0.08
     Mund
    0.08
     zap
    0.08
    Activations Density 0.000%

    No Known Activations