© 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. 4330
    Prev
    Next
    INDEX
    Explanations

    romantic partners

    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
     baj
    -0.09
     Uncle
    -0.08
    rip
    -0.08
    uga
    -0.08
    tres
    -0.08
     Lester
    -0.08
    [Unit
    -0.07
    åºĵ
    -0.07
     Lip
    -0.07
     trop
    -0.07
    POSITIVE LOGITS
     partner
    0.53
     partners
    0.46
     Partner
    0.43
    partner
    0.43
     spouse
    0.41
    Partner
    0.41
     partnered
    0.40
     spouses
    0.37
     partnering
    0.37
     girlfriend
    0.37
    Activations Density 0.534%

    No Known Activations