© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113913
    Prev
    Next
    INDEX
    Explanations

    you can

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     wink
    -0.13
     correctly
    -0.12
     refr
    -0.12
    adian
    -0.10
     clearly
    -0.10
     Paz
    -0.10
     Fraser
    -0.09
     cleanly
    -0.09
     conver
    -0.09
    wow
    -0.09
    POSITIVE LOGITS
     Bj
    0.09
     competitiveness
    0.08
     Brewer
    0.08
     Lust
    0.08
    ży
    0.08
     canceled
    0.08
     maximal
    0.08
    ...">↵
    0.08
     eff
    0.08
    &m
    0.08
    Activations Density 0.004%

    No Known Activations