© 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. 58215
    Prev
    Next
    INDEX
    Explanations

    Dirac fermions, Fermi surfaces, topology

    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
     frog
    -0.08
     Salt
    -0.08
     salt
    -0.08
     âĢķ
    -0.08
    iker
    -0.08
    в
    -0.07
    Crow
    -0.07
    brook
    -0.07
    ween
    -0.07
     crow
    -0.07
    POSITIVE LOGITS
     Merc
    0.09
    viso
    0.09
    ABA
    0.09
    lei
    0.09
    .Mark
    0.09
     kurs
    0.09
    .Spring
    0.08
     Artem
    0.08
    gne
    0.08
     evenly
    0.08
    Activations Density 0.006%

    No Known Activations