© 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. 3903
    Prev
    Next
    INDEX
    Explanations

    numbers and years

    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
     Locator
    -0.08
    stan
    -0.08
     bound
    -0.08
     wah
    -0.08
     decis
    -0.07
     horn
    -0.07
    loc
    -0.07
    furt
    -0.07
    allery
    -0.07
    rans
    -0.07
    POSITIVE LOGITS
    unga
    0.10
     airs
    0.09
    +↵
    0.09
     Jama
    0.09
    âĢij
    0.09
     Matter
    0.09
     Separate
    0.09
     paired
    0.09
     Duo
    0.09
    NX
    0.09
    Activations Density 0.204%

    No Known Activations