© 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. 112005
    Prev
    Next
    INDEX
    Explanations

    love and care

    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
     Loves
    -0.11
     Love
    -0.11
     Locke
    -0.10
     liberalism
    -0.10
     LOVE
    -0.10
    Labels
    -0.10
    .Strings
    -0.10
     Cable
    -0.10
     Romance
    -0.10
    -loving
    -0.10
    POSITIVE LOGITS
     Hate
    0.13
     hate
    0.12
    WND
    0.10
     Attention
    0.09
     hated
    0.09
     attention
    0.09
     sacrifice
    0.09
     hates
    0.09
     Bris
    0.08
    ủ
    0.08
    Activations Density 0.119%

    No Known Activations