© 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. 113713
    Prev
    Next
    INDEX
    Explanations

    This followed by study or article

    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
     Kund
    -0.10
     swims
    -0.10
     meant
    -0.09
     Bath
    -0.09
     waving
    -0.09
     Ton
    -0.09
     Swim
    -0.08
     topped
    -0.08
     swimming
    -0.08
     filled
    -0.08
    POSITIVE LOGITS
     narrative
    0.11
     chapter
    0.10
     Narrative
    0.10
    387
    0.10
     vign
    0.09
    /lg
    0.09
     collateral
    0.09
    inium
    0.09
    assage
    0.09
     humble
    0.09
    Activations Density 0.003%

    No Known Activations