© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16167
    Prev
    Next
    INDEX
    Explanations

    social networking and interpersonal connections

    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
     abortion
    -0.09
     refund
    -0.08
     abdom
    -0.08
     ownership
    -0.08
     Precision
    -0.08
     punitive
    -0.08
    recision
    -0.08
     covering
    -0.08
     myths
    -0.08
     compensation
    -0.08
    POSITIVE LOGITS
     social
    0.38
     networking
    0.36
     interpersonal
    0.35
     Networking
    0.35
     Social
    0.35
     friendships
    0.34
    social
    0.33
    Social
    0.32
     SOCIAL
    0.31
    -social
    0.30
    Activations Density 0.883%

    No Known Activations