© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114238
    Prev
    Next
    INDEX
    Explanations

    drawing 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
    Not in Any Lists

    No Comments

    Negative Logits
    oric
    -0.10
     forfe
    -0.10
    hammad
    -0.10
    daq
    -0.10
     recalled
    -0.10
     knowingly
    -0.10
    rier
    -0.10
    äº
    -0.10
     uphill
    -0.09
     Alam
    -0.09
    POSITIVE LOGITS
     conclusion
    0.61
     conclusions
    0.60
     Conclusion
    0.49
     conclude
    0.49
     concluded
    0.46
    Conclusion
    0.46
     concl
    0.42
     concludes
    0.41
     concluding
    0.40
     inference
    0.37
    Activations Density 0.538%

    No Known Activations