© 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. 49432
    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
    iage
    -0.11
     Salv
    -0.09
     Thorn
    -0.09
    Ãļ
    -0.08
    Pag
    -0.08
     ladder
    -0.08
    ário
    -0.08
    /orders
    -0.08
     Moy
    -0.08
     SS
    -0.08
    POSITIVE LOGITS
     lies
    0.10
    chia
    0.09
     span
    0.09
    leo
    0.09
     Zar
    0.09
     sever
    0.09
     bed
    0.09
     cad
    0.09
    cea
    0.09
    stad
    0.08
    Activations Density 0.000%

    No Known Activations