© 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. 1375
    Prev
    Next
    INDEX
    Explanations

    meta-analysis study comparison

    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
     prepar
    -0.10
    Characteristic
    -0.09
     accesses
    -0.09
     prat
    -0.08
     aides
    -0.08
     ther
    -0.08
     practiced
    -0.08
     cong
    -0.08
     slips
    -0.08
    zem
    -0.08
    POSITIVE LOGITS
     statistically
    0.17
     pooled
    0.17
     study
    0.16
     data
    0.16
     statistical
    0.15
     comparing
    0.14
     studies
    0.14
     cohort
    0.14
     epidemi
    0.14
     comparisons
    0.14
    Activations Density 3.054%

    No Known Activations