© 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. 2500
    Prev
    Next
    INDEX
    Explanations

    cancel button, heavy metals, germinal cells, compute nodes, endothelial, emission spectra, clutch actuation, front wheel, Stopwatch

    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
    oure
    -0.08
    our
    -0.08
    ips
    -0.07
    loc
    -0.07
    etro
    -0.06
     Flat
    -0.06
    guard
    -0.06
    ¢
    -0.06
    aul
    -0.06
     Kub
    -0.06
    POSITIVE LOGITS
    agus
    0.12
    ALER
    0.10
     Tobias
    0.10
    linger
    0.10
    bij
    0.10
    ernes
    0.10
    iglia
    0.10
     Boo
    0.10
    arters
    0.10
    isos
    0.10
    Activations Density 1.028%

    No Known Activations