© 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. 46562
    Prev
    Next
    INDEX
    Explanations

    such a/an [example]

    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
     Hag
    -0.10
     pend
    -0.09
     ench
    -0.09
    ::<
    -0.08
     Bronze
    -0.08
     excursion
    -0.08
     Hampton
    -0.08
    ë¦Ħ
    -0.08
    936
    -0.08
    PF
    -0.08
    POSITIVE LOGITS
    cars
    0.09
     Eg
    0.09
    .news
    0.09
    large
    0.09
     Eyes
    0.09
     Sek
    0.09
     tossing
    0.09
    anja
    0.09
    .rpc
    0.09
    å²ģ
    0.09
    Activations Density 0.023%

    No Known Activations