© 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. 115819
    Prev
    Next
    INDEX
    Explanations

    events surrounding

    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
     scraped
    -0.10
    voy
    -0.08
     Lim
    -0.08
    asd
    -0.08
     greedy
    -0.07
    alan
    -0.07
     laut
    -0.07
    ikal
    -0.07
    eldorf
    -0.07
     condition
    -0.07
    POSITIVE LOGITS
     events
    0.25
    /events
    0.22
     Events
    0.21
    events
    0.20
    (events
    0.19
    -events
    0.19
     preceding
    0.18
    Events
    0.18
     unfold
    0.18
     unfolding
    0.17
    Activations Density 0.054%

    No Known Activations