© 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. 28673
    Prev
    Next
    INDEX
    Explanations

    unexpected events or encounters

    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
     Saying
    -0.09
     orgas
    -0.08
     Beds
    -0.08
    adel
    -0.08
     defer
    -0.07
     tenga
    -0.07
     Kod
    -0.07
     SAY
    -0.07
     Extraction
    -0.07
     drip
    -0.07
    POSITIVE LOGITS
     accidentally
    0.28
     luck
    0.27
     unexpectedly
    0.27
     stumble
    0.26
     stumbled
    0.26
     unsus
    0.25
     unlucky
    0.25
     encountering
    0.25
     encounter
    0.24
     accidental
    0.24
    Activations Density 0.148%

    No Known Activations