© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55470
    Prev
    Next
    INDEX
    Explanations

    for example,

    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
    corp
    -0.09
    bai
    -0.09
    UCT
    -0.09
    pps
    -0.09
    -du
    -0.08
    emax
    -0.08
    iek
    -0.08
    IClient
    -0.08
     eg
    -0.08
    ulary
    -0.08
    POSITIVE LOGITS
    eries
    0.09
     ones
    0.08
    unes
    0.08
    ich
    0.08
    ander
    0.07
    rus
    0.07
    Camb
    0.07
     Hun
    0.07
    Others
    0.07
    snap
    0.07
    Activations Density 0.016%

    No Known Activations