© 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. 46879
    Prev
    Next
    INDEX
    Explanations

    recent past and future events

    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
     future
    -0.10
     circa
    -0.09
     youre
    -0.08
    future
    -0.07
    ambi
    -0.07
     galer
    -0.07
    UTURE
    -0.07
    _future
    -0.07
    NEXT
    -0.07
    -era
    -0.07
    POSITIVE LOGITS
     recently
    0.70
     yesterday
    0.67
     Recently
    0.57
     Yesterday
    0.56
     recent
    0.54
     today
    0.53
    Yesterday
    0.53
    recent
    0.53
    Recently
    0.52
     tonight
    0.47
    Activations Density 3.307%

    No Known Activations