© 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. 17056
    Prev
    Next
    INDEX
    Explanations

    death and mortality

    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
     masculine
    -0.14
     masculinity
    -0.12
     sexist
    -0.12
     femin
    -0.12
     feminine
    -0.12
     mascul
    -0.11
     stereotype
    -0.11
     dames
    -0.11
     testosterone
    -0.11
     blames
    -0.11
    POSITIVE LOGITS
     death
    0.33
    Death
    0.30
     Death
    0.29
    -death
    0.28
    death
    0.27
     mortality
    0.25
     immortal
    0.25
     dying
    0.23
    _death
    0.22
    ortality
    0.21
    Activations Density 0.381%

    No Known Activations