© 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. 3653
    Prev
    Next
    INDEX
    Explanations

    single, repeated, longitudinal, simultaneous measurements

    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
     ph
    -0.08
     tap
    -0.08
    uche
    -0.08
    ron
    -0.08
    olle
    -0.07
    tl
    -0.07
     modified
    -0.07
     Approx
    -0.07
    tap
    -0.07
     posed
    -0.07
    POSITIVE LOGITS
     intimately
    0.11
     fortunately
    0.11
     compreh
    0.11
     unprecedented
    0.11
     sage
    0.10
     hindsight
    0.10
     matched
    0.10
     painstaking
    0.10
     decis
    0.10
     explicitly
    0.10
    Activations Density 0.665%

    No Known Activations