© 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. 1326
    Prev
    Next
    INDEX
    Explanations

    start actions or states

    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
    completion
    -0.13
     starting
    -0.11
    _completion
    -0.11
     startup
    -0.11
    itch
    -0.11
    	namespace
    -0.10
    ITCH
    -0.10
    Away
    -0.10
     completion
    -0.10
    tsy
    -0.10
    POSITIVE LOGITS
     anew
    0.14
    /end
    0.14
    nings
    0.12
     work
    0.10
     af
    0.10
    /st
    0.10
    le
    0.09
     negotiations
    0.09
     proceedings
    0.09
    pped
    0.09
    Activations Density 0.565%

    No Known Activations