© 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. 54285
    Prev
    Next
    INDEX
    Explanations

    Asst. U.S. Atty

    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
    olib
    -0.08
    ĥģ
    -0.08
    rost
    -0.08
     Stanton
    -0.08
     Sant
    -0.08
    .publisher
    -0.08
    ChangeEvent
    -0.07
     ach
    -0.07
    .public
    -0.07
    rut
    -0.07
    POSITIVE LOGITS
     Ske
    0.09
    ceu
    0.09
    ours
    0.08
     none
    0.08
     Epidemi
    0.08
     motion
    0.08
     anyways
    0.08
     qual
    0.08
    ocene
    0.08
     neither
    0.08
    Activations Density 0.006%

    No Known Activations