© 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. 33082
    Prev
    Next
    INDEX
    Explanations

    time durations followed by past/future indicators

    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
     lately
    -0.11
    entered
    -0.10
    OVE
    -0.10
     infring
    -0.10
     Seah
    -0.10
    endon
    -0.10
    çª
    -0.10
    recent
    -0.10
    nton
    -0.09
     squeezing
    -0.09
    POSITIVE LOGITS
     intervening
    0.15
     lapse
    0.10
     temporal
    0.08
     Gol
    0.08
     Passage
    0.08
    -memory
    0.08
     Memory
    0.08
     Dexter
    0.08
    ledge
    0.08
     predecessor
    0.07
    Activations Density 0.145%

    No Known Activations