© 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. 116412
    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
    illy
    -0.10
     Bush
    -0.08
     accessor
    -0.08
    ela
    -0.08
    /options
    -0.08
    ancia
    -0.08
     kre
    -0.08
    uka
    -0.08
    olan
    -0.07
     Cah
    -0.07
    POSITIVE LOGITS
     Tos
    0.11
     presum
    0.10
     HuffPost
    0.10
     distinctly
    0.10
     departed
    0.10
     murky
    0.09
     mutil
    0.09
     Wolff
    0.09
     Depart
    0.09
    exo
    0.09
    Activations Density 0.000%

    No Known Activations