© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90053
    Prev
    Next
    INDEX
    Explanations

    the incident or accident

    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
     tallest
    -0.11
     reigning
    -0.09
     fatt
    -0.08
     giver
    -0.08
    unce
    -0.08
     right
    -0.08
     else
    -0.08
     finest
    -0.08
     opponent
    -0.08
     exiting
    -0.08
    POSITIVE LOGITS
     incident
    0.19
     accident
    0.16
     incidents
    0.14
    incident
    0.13
     conversation
    0.13
     ult
    0.13
     spat
    0.12
     comment
    0.12
     skipped
    0.12
     attempted
    0.12
    Activations Density 0.135%

    No Known Activations