© 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. 112855
    Prev
    Next
    INDEX
    Explanations

    "the" followed by time/event 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
     Sutton
    -0.11
     Gee
    -0.10
    stamp
    -0.10
    ASP
    -0.10
    subst
    -0.10
    rese
    -0.10
    toast
    -0.10
     Licht
    -0.10
     lect
    -0.10
    kB
    -0.09
    POSITIVE LOGITS
     era
    0.12
     eve
    0.11
     time
    0.10
     moment
    0.10
     beginning
    0.10
     headquarters
    0.10
     case
    0.09
     year
    0.09
     fate
    0.09
     place
    0.08
    Activations Density 0.071%

    No Known Activations