© 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. 33725
    Prev
    Next
    INDEX
    Explanations

    suddenly or unexpectedly happens

    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
     inadvert
    -0.13
     accidentally
    -0.13
     inadvertently
    -0.13
     hastily
    -0.11
     creeping
    -0.11
     accidental
    -0.11
     knowingly
    -0.10
     longitud
    -0.10
     unintention
    -0.10
     ssize
    -0.10
    POSITIVE LOGITS
     suddenly
    0.18
     Suddenly
    0.15
    Suddenly
    0.13
     overnight
    0.12
     Estr
    0.11
     decides
    0.10
    essa
    0.10
    uddenly
    0.10
     BAM
    0.10
     Overnight
    0.10
    Activations Density 0.062%

    No Known Activations