© 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. 117052
    Prev
    Next
    INDEX
    Explanations

    loss of parents or spouse

    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
    idot
    -0.11
    ikal
    -0.09
    elas
    -0.08
    azzi
    -0.08
    ird
    -0.08
    chy
    -0.08
     lapse
    -0.08
    enet
    -0.08
     convey
    -0.08
     Examiner
    -0.08
    POSITIVE LOGITS
     parents
    0.25
     deceased
    0.24
     wife
    0.20
     Parents
    0.20
    parents
    0.20
     deaths
    0.19
     dead
    0.19
     spouses
    0.19
    Parents
    0.18
     tragedies
    0.18
    Activations Density 0.166%

    No Known Activations