© 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. 7773
    Prev
    Next
    INDEX
    Explanations

    loss of loved ones

    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
     Dias
    -0.12
     successors
    -0.10
     Pearce
    -0.09
     newcomers
    -0.09
     surviving
    -0.09
     bored
    -0.09
     discontinued
    -0.09
     silhouette
    -0.09
     Bere
    -0.09
     smarty
    -0.08
    POSITIVE LOGITS
     beloved
    0.22
     loved
    0.20
     Loved
    0.15
     prematurely
    0.14
     cherished
    0.13
     liked
    0.13
     infant
    0.12
     valued
    0.12
     companion
    0.12
     innocence
    0.11
    Activations Density 0.420%

    No Known Activations