© 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. 1251
    Prev
    Next
    INDEX
    Explanations

    nutritional health and bodily substances

    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
    )new
    -0.09
    etal
    -0.09
    olt
    -0.09
    579
    -0.08
    side
    -0.08
    illard
    -0.08
    ylon
    -0.08
     implementation
    -0.08
     запиÑģ
    -0.08
    ::$
    -0.08
    POSITIVE LOGITS
    (er
    0.09
    /from
    0.08
     _______,
    0.08
     water
    0.08
     voc
    0.08
     commemorate
    0.08
    /use
    0.08
     domestically
    0.07
    æĹı
    0.07
     _,
    0.07
    Activations Density 4.729%

    No Known Activations