© 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. 47583
    Prev
    Next
    INDEX
    Explanations

    family and friends gatherings

    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
     Brothers
    -0.10
     ($.
    -0.10
    ometown
    -0.10
     elig
    -0.10
    Students
    -0.10
     brothers
    -0.10
    odor
    -0.10
     roommate
    -0.10
    estr
    -0.09
     pimp
    -0.09
    POSITIVE LOGITS
     couples
    0.18
     neighbour
    0.15
     neighbor
    0.15
     friendship
    0.15
     neighbors
    0.14
     RSVP
    0.14
     neighbours
    0.14
     Friendship
    0.14
     golf
    0.14
     Couples
    0.14
    Activations Density 0.086%

    No Known Activations