© 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. 111381
    Prev
    Next
    INDEX
    Explanations

    reached a conclusion

    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
    kie
    -0.09
    '%(
    -0.08
    iez
    -0.08
     McGill
    -0.08
    296
    -0.07
     intim
    -0.07
     Aston
    -0.07
    (tf
    -0.07
    sect
    -0.07
     Wend
    -0.07
    POSITIVE LOGITS
     concluded
    0.29
     conclusion
    0.25
     conclusions
    0.24
     conclude
    0.23
     concludes
    0.22
     Conclusion
    0.20
    Conclusion
    0.20
     concl
    0.17
     concluding
    0.17
     decided
    0.16
    Activations Density 0.155%

    No Known Activations