© 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. 32220
    Prev
    Next
    INDEX
    Explanations

    conclude or 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
    Not in Any Lists

    No Comments

    Negative Logits
     Basics
    -0.10
    ucker
    -0.10
     Basic
    -0.10
    -basic
    -0.10
     basic
    -0.09
    /basic
    -0.09
    Basic
    -0.09
     Definition
    -0.08
     basics
    -0.08
     Initial
    -0.08
    POSITIVE LOGITS
     Conclusion
    0.38
    Conclusion
    0.37
     conclusion
    0.31
     concluding
    0.25
     Future
    0.25
     conclude
    0.25
     conclusions
    0.24
     concludes
    0.24
     Final
    0.24
     Miscellaneous
    0.23
    Activations Density 0.108%

    No Known Activations