© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33866
    Prev
    Next
    INDEX
    Explanations

    collective action or group work

    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
     solo
    -0.11
     Alone
    -0.11
     imperson
    -0.10
    oui
    -0.10
     advent
    -0.10
     alone
    -0.10
    perc
    -0.10
    anders
    -0.10
     Variation
    -0.10
     duo
    -0.09
    POSITIVE LOGITS
     collectively
    0.35
     collective
    0.24
     themselves
    0.23
     clustered
    0.23
     unanimously
    0.22
     outnumber
    0.21
     flock
    0.21
     Collective
    0.19
     congreg
    0.18
     grouped
    0.18
    Activations Density 0.489%

    No Known Activations