© 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. 50601
    Prev
    Next
    INDEX
    Explanations

    perhaps the most

    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
     frankly
    -0.11
     apparently
    -0.11
     undoubtedly
    -0.10
     plenty
    -0.10
     recently
    -0.09
     Cors
    -0.09
     Pilot
    -0.09
    zano
    -0.09
    yps
    -0.09
    "&
    -0.09
    POSITIVE LOGITS
     TOO
    0.12
     overall
    0.10
    PLL
    0.09
     biggest
    0.09
     greatest
    0.09
     Unique
    0.09
     happiest
    0.09
     owing
    0.09
     summed
    0.08
     (?)
    0.08
    Activations Density 0.100%

    No Known Activations