© 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. 15181
    Prev
    Next
    INDEX
    Explanations

    sudden violent incidents

    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
     temporarily
    -0.10
    de
    -0.10
     nearby
    -0.10
     canned
    -0.10
     Nearby
    -0.09
     Temporary
    -0.09
     TEMP
    -0.09
    avo
    -0.09
     Ceiling
    -0.09
     subsequently
    -0.09
    POSITIVE LOGITS
     unexpectedly
    0.24
     unsus
    0.20
     unexpected
    0.20
     suddenly
    0.19
     surprise
    0.18
    unexpected
    0.18
     sudden
    0.18
     Surprise
    0.18
     abruptly
    0.17
     Unexpected
    0.17
    Activations Density 0.130%

    No Known Activations