© 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. 4129
    Prev
    Next
    INDEX
    Explanations

    China, Chinese, traditional, herbal

    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
     Lynn
    -0.10
    .Verify
    -0.09
     perv
    -0.09
    Twig
    -0.09
    uti
    -0.09
    printer
    -0.09
    lingen
    -0.09
    mites
    -0.09
     Grass
    -0.09
    xit
    -0.09
    POSITIVE LOGITS
    trl
    0.09
    elo
    0.08
    elor
    0.08
     Jaw
    0.08
    urn
    0.08
    ett
    0.07
    redd
    0.07
    etti
    0.07
     ho
    0.07
     leveled
    0.07
    Activations Density 0.114%

    No Known Activations