© 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. 91629
    Prev
    Next
    INDEX
    Explanations

    cooperation

    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
    jak
    -0.11
    uyo
    -0.10
    ych
    -0.10
     Anchor
    -0.10
    uma
    -0.10
    ola
    -0.10
    Matchers
    -0.10
     Anch
    -0.09
     surpr
    -0.09
     Compression
    -0.09
    POSITIVE LOGITS
     cooperation
    0.58
     cooperate
    0.58
     cooper
    0.57
     cooperating
    0.56
     cooperative
    0.52
     Cooperation
    0.50
     Cooper
    0.48
     Cooperative
    0.42
     coop
    0.40
    coop
    0.29
    Activations Density 0.281%

    No Known Activations