© 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. 114251
    Prev
    Next
    INDEX
    Explanations

    time delayed

    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
     Short
    -0.13
     shorten
    -0.11
     short
    -0.11
    -short
    -0.11
    Short
    -0.10
     shorter
    -0.10
     quickly
    -0.10
    785
    -0.09
     SHORT
    -0.09
     Soon
    -0.09
    POSITIVE LOGITS
     delayed
    0.32
     postponed
    0.29
     distant
    0.26
     deferred
    0.25
     Delay
    0.25
    Delayed
    0.23
     delay
    0.23
     postpone
    0.23
     wait
    0.22
     tard
    0.22
    Activations Density 0.562%

    No Known Activations