© 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. 32440
    Prev
    Next
    INDEX
    Explanations

    past tense statements mentioning time

    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
     recently
    -0.17
     occasionally
    -0.15
     regularly
    -0.15
     occasional
    -0.15
     later
    -0.14
     eventually
    -0.14
     someday
    -0.14
     Recently
    -0.14
    recent
    -0.13
     frequently
    -0.12
    POSITIVE LOGITS
    achen
    0.10
     Stam
    0.10
     reminded
    0.10
     conversation
    0.09
    alon
    0.09
    903
    0.09
    unu
    0.09
     revis
    0.09
     someone
    0.09
     Reminder
    0.09
    Activations Density 0.618%

    No Known Activations