© 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. 55482
    Prev
    Next
    INDEX
    Explanations

    meditation and related practices

    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
    /fr
    -0.11
    ern
    -0.10
    bury
    -0.10
    æ³
    -0.10
     Investigators
    -0.09
    ities
    -0.09
    ies
    -0.09
    imitive
    -0.09
    ury
    -0.09
    orida
    -0.09
    POSITIVE LOGITS
    atore
    0.08
     cris
    0.08
     Gur
    0.08
     crystall
    0.07
    hall
    0.07
    .dictionary
    0.07
     Tos
    0.07
     Kund
    0.07
    wait
    0.07
     Platform
    0.07
    Activations Density 0.004%

    No Known Activations