© 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. 3366
    Prev
    Next
    INDEX
    Explanations

    come to terms or conclusions

    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
     grant
    -0.07
     succeeding
    -0.07
    ingroup
    -0.07
     grosse
    -0.06
    rell
    -0.06
    grant
    -0.06
     Deb
    -0.06
    /reference
    -0.06
    iete
    -0.06
     Kelvin
    -0.06
    POSITIVE LOGITS
     conclusions
    0.34
     conclusion
    0.33
     Conclusion
    0.22
    Conclusion
    0.21
     concl
    0.21
     verdict
    0.19
     decisions
    0.19
     consensus
    0.19
     concluded
    0.18
     conclude
    0.18
    Activations Density 0.067%

    No Known Activations