© 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. 5944
    Prev
    Next
    INDEX
    Explanations

    exclamations of relief, exertion, surprise

    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
     deepen
    -0.10
    lien
    -0.10
    anian
    -0.10
    itsu
    -0.09
    /pi
    -0.09
    ######
    -0.09
     crumbling
    -0.09
    Ñıз
    -0.09
     prolifer
    -0.09
    ippi
    -0.09
    POSITIVE LOGITS
     breath
    0.13
     exhausting
    0.11
     breathe
    0.10
     finally
    0.10
     breathed
    0.10
     gust
    0.10
     sweating
    0.10
    pressure
    0.09
     exh
    0.09
     Exhaust
    0.09
    Activations Density 0.001%

    No Known Activations