© 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. 18313
    Prev
    Next
    INDEX
    Explanations

    caring for others

    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
    isson
    -0.08
    _cd
    -0.08
    kaar
    -0.08
    ly
    -0.08
     unclear
    -0.08
     Fraction
    -0.08
     periodically
    -0.08
     credibility
    -0.08
    /accounts
    -0.08
     clar
    -0.08
    POSITIVE LOGITS
     cared
    0.12
     caring
    0.11
     care
    0.10
    .xhtml
    0.10
     nurturing
    0.10
     cub
    0.09
     Care
    0.09
    (AT
    0.09
    zin
    0.09
     bubb
    0.09
    Activations Density 0.123%

    No Known Activations