© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2588
    Prev
    Next
    INDEX
    Explanations

    conclusion / final

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aset
    -0.10
     Anatomy
    -0.09
     flesh
    -0.09
    irs
    -0.08
     meticulously
    -0.08
     Basic
    -0.08
    ovel
    -0.08
    rieb
    -0.08
     Basics
    -0.08
     Picker
    -0.08
    POSITIVE LOGITS
     conclusion
    0.22
    Conclusion
    0.22
     Conclusion
    0.22
     concluding
    0.20
     conclusions
    0.19
     conclude
    0.19
     concludes
    0.17
     final
    0.17
     Final
    0.16
     concluded
    0.16
    Activations Density 0.157%

    No Known Activations