© 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. 55829
    Prev
    Next
    INDEX
    Explanations

    dating back decades or centuries

    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
     rumors
    -0.09
    appe
    -0.09
     rumours
    -0.09
    Appe
    -0.09
     Appe
    -0.08
     earlier
    -0.08
     infinit
    -0.08
    unittest
    -0.08
     memories
    -0.08
    culate
    -0.08
    POSITIVE LOGITS
    Diamond
    0.10
     Normal
    0.09
    onom
    0.09
    _bases
    0.09
     Diamond
    0.09
    FTA
    0.09
    asan
    0.09
    allo
    0.09
     Bali
    0.08
     Gold
    0.08
    Activations Density 0.058%

    No Known Activations