© 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. 6587
    Prev
    Next
    INDEX
    Explanations

    love and relationships

    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
     synerg
    -0.08
     soothing
    -0.07
     spas
    -0.07
     disconnect
    -0.07
     Rubin
    -0.07
    eut
    -0.07
     omit
    -0.07
     abolish
    -0.07
     Boeh
    -0.07
     Dou
    -0.07
    POSITIVE LOGITS
     relationships
    0.25
     dating
    0.25
     flirt
    0.25
     romant
    0.25
     romance
    0.25
     Dating
    0.24
     Relationships
    0.23
     flirting
    0.23
    Relationship
    0.21
     crush
    0.21
    Activations Density 0.127%

    No Known Activations