© 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. 30943
    Prev
    Next
    INDEX
    Explanations

    later or afterwards

    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
    Maybe
    -0.12
     frankly
    -0.11
     maybe
    -0.10
     perhaps
    -0.10
     honestly
    -0.10
     ding
    -0.10
    gan
    -0.09
     Honestly
    -0.09
     Maybe
    -0.09
     Gone
    -0.09
    POSITIVE LOGITS
     Later
    0.23
     Afterwards
    0.23
    Later
    0.21
     later
    0.21
     Meanwhile
    0.18
     afterwards
    0.17
     Eventually
    0.17
     After
    0.17
    Meanwhile
    0.17
     Unable
    0.16
    Activations Density 0.353%

    No Known Activations