© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48242
    Prev
    Next
    INDEX
    Explanations

    compassion and empathy

    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
     obedient
    -0.12
     fou
    -0.11
     conced
    -0.11
     secretive
    -0.11
     compliment
    -0.11
     obsessive
    -0.11
     Transparent
    -0.11
     tame
    -0.11
     Secrets
    -0.11
     trust
    -0.10
    POSITIVE LOGITS
     compassion
    0.39
     empathy
    0.36
     compassionate
    0.34
     empath
    0.33
     Compass
    0.31
     sympathy
    0.30
     sympath
    0.29
    compass
    0.27
     sympathetic
    0.26
     humanitarian
    0.25
    Activations Density 0.158%

    No Known Activations