© 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. 90001
    Prev
    Next
    INDEX
    Explanations

    eventually followed by consequence

    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
     liked
    -0.09
    eri
    -0.08
     outnumber
    -0.08
     Mill
    -0.08
     SM
    -0.08
     primarily
    -0.08
     expressly
    -0.08
     smelled
    -0.07
     beaten
    -0.07
     contain
    -0.07
    POSITIVE LOGITS
     ensued
    0.18
     soon
    0.17
     led
    0.17
     notwithstanding
    0.16
     finally
    0.16
     suddenly
    0.16
     lead
    0.15
     prompted
    0.15
     prompts
    0.15
     eventually
    0.15
    Activations Density 0.365%

    No Known Activations