© 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. 26601
    Prev
    Next
    INDEX
    Explanations

    crowds and 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
     singleton
    -0.12
     Floors
    -0.12
    ROOM
    -0.11
     roommate
    -0.11
     nurs
    -0.11
     shel
    -0.11
     patented
    -0.11
     perpet
    -0.11
     anonymously
    -0.10
     handbook
    -0.10
    POSITIVE LOGITS
     crowds
    0.29
     crowd
    0.28
     Crowd
    0.21
     gathered
    0.20
     gathering
    0.19
    crow
    0.18
     crowded
    0.18
     tents
    0.17
     spectators
    0.17
     assembled
    0.16
    Activations Density 0.249%

    No Known Activations