© 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. 47787
    Prev
    Next
    INDEX
    Explanations

    heart and related concepts

    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
    tod
    -0.09
    oundary
    -0.09
    anto
    -0.09
    _major
    -0.08
     major
    -0.08
     paraph
    -0.08
     subur
    -0.08
     pro
    -0.08
    PILE
    -0.08
    shan
    -0.08
    POSITIVE LOGITS
     hearts
    0.51
     heart
    0.38
     Hearts
    0.38
    heart
    0.33
     Heart
    0.31
    -heart
    0.29
    å¿ĥ
    0.29
    Heart
    0.28
    -hearted
    0.22
     souls
    0.21
    Activations Density 0.096%

    No Known Activations