© 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. 115373
    Prev
    Next
    INDEX
    Explanations

    until / eventually / later

    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
     innoc
    -0.10
     inherit
    -0.09
     innocent
    -0.09
     idle
    -0.09
    isd
    -0.08
     immediately
    -0.08
     Mattis
    -0.08
     predatory
    -0.08
     recogn
    -0.08
     summar
    -0.08
    POSITIVE LOGITS
    until
    0.16
     until
    0.16
     eventually
    0.15
     eventual
    0.14
     Eventually
    0.13
     till
    0.12
    Eventually
    0.12
     Later
    0.12
    _until
    0.12
    Later
    0.12
    Activations Density 0.047%

    No Known Activations