© 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. 48536
    Prev
    Next
    INDEX
    Explanations

    offer comfort or sympathy

    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
     lazy
    -0.11
     stricter
    -0.11
     request
    -0.11
    lazy
    -0.11
     endanger
    -0.11
    requests
    -0.11
     rar
    -0.11
    utra
    -0.10
    _request
    -0.10
    agram
    -0.10
    POSITIVE LOGITS
     sympath
    0.52
     sympathy
    0.49
     sympathetic
    0.48
     empath
    0.45
     comforting
    0.44
     empathy
    0.40
     comfort
    0.36
     consolation
    0.36
     compassion
    0.33
     comforts
    0.33
    Activations Density 0.237%

    No Known Activations