© 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. 49063
    Prev
    Next
    INDEX
    Explanations

    participate or participation

    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
     struck
    -0.11
    uers
    -0.10
     Bere
    -0.10
     Tune
    -0.09
    igers
    -0.09
    hatt
    -0.09
     GV
    -0.09
     Pip
    -0.09
    INES
    -0.09
     Hale
    -0.09
    POSITIVE LOGITS
     participation
    0.17
     participate
    0.17
     Participation
    0.15
    /part
    0.14
     particip
    0.14
     participated
    0.14
     Particip
    0.13
     participates
    0.13
     participating
    0.13
     actively
    0.12
    Activations Density 0.034%

    No Known Activations