© 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. 29327
    Prev
    Next
    INDEX
    Explanations

    dating, conversations, affection, scheduling

    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
    /an
    -0.10
     hiring
    -0.09
     inherited
    -0.09
     anonymously
    -0.09
     Hiring
    -0.08
     Vog
    -0.08
    aria
    -0.08
    -blind
    -0.08
     Fired
    -0.08
    /pol
    -0.08
    POSITIVE LOGITS
     texting
    0.20
     outings
    0.18
     weekends
    0.17
     affection
    0.17
     intimacy
    0.16
     weekend
    0.16
     schedules
    0.15
     scheduling
    0.14
     cudd
    0.14
     meetings
    0.14
    Activations Density 0.011%

    No Known Activations