© 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. 25912
    Prev
    Next
    INDEX
    Explanations

    accidentally or unexpectedly

    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
     vain
    -0.09
     swore
    -0.09
     proceeding
    -0.08
     coherent
    -0.08
     had
    -0.08
     african
    -0.08
    agi
    -0.08
     coherence
    -0.08
     lasted
    -0.08
     feeder
    -0.07
    POSITIVE LOGITS
     unexpectedly
    0.17
     accidentally
    0.15
     unexpected
    0.14
     accidental
    0.12
     blir
    0.12
     accident
    0.12
    unexpected
    0.11
     Beste
    0.11
     resc
    0.11
     discovers
    0.11
    Activations Density 0.101%

    No Known Activations