© 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. 25986
    Prev
    Next
    INDEX
    Explanations

    drowning and sinking 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
     trail
    -0.11
     massage
    -0.10
    trail
    -0.10
     runner
    -0.10
     trails
    -0.09
     sanit
    -0.09
     shielding
    -0.09
    astle
    -0.09
     runners
    -0.09
     Olympia
    -0.09
    POSITIVE LOGITS
     drowning
    0.34
     drown
    0.29
     drowned
    0.28
     sinking
    0.20
     rescue
    0.20
     Rescue
    0.19
     sink
    0.19
     resc
    0.18
     sank
    0.17
     rescued
    0.17
    Activations Density 0.162%

    No Known Activations