© 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. 3614
    Prev
    Next
    INDEX
    Explanations

    willingness to participate

    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
    Negative Logits
    olor
    -0.10
    ICA
    -0.09
     Deluxe
    -0.08
     contempor
    -0.08
    æ¡
    -0.08
     Buzz
    -0.08
    isch
    -0.08
     BMC
    -0.08
     Lor
    -0.08
     feeling
    -0.08
    POSITIVE LOGITS
     willingness
    0.23
     willing
    0.19
     eag
    0.17
     eagerly
    0.16
     eager
    0.14
     acceptance
    0.14
     willingly
    0.13
     readily
    0.13
     Eag
    0.12
     readiness
    0.12
    Activations Density 0.033%

    No Known Activations