© 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. 6536
    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
     nag
    -0.08
     pay
    -0.07
     rav
    -0.07
     precip
    -0.07
    ynam
    -0.07
     honest
    -0.07
     ones
    -0.07
     Dynam
    -0.07
    ...
    -0.07
     Seam
    -0.06
    POSITIVE LOGITS
    proc
    0.13
    /options
    0.13
    -options
    0.13
    ewise
    0.12
    Options
    0.12
     proc
    0.12
    semb
    0.12
     sourcing
    0.12
     option
    0.12
     Options
    0.12
    Activations Density 0.000%

    No Known Activations