© 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. 58332
    Prev
    Next
    INDEX
    Explanations

    holographic, symmetry, matching, theory, ologist

    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
     fle
    -0.09
    gra
    -0.08
    ocab
    -0.08
     recurring
    -0.08
     cris
    -0.08
     dej
    -0.07
     Tess
    -0.07
    adian
    -0.07
     Frag
    -0.07
    yll
    -0.07
    POSITIVE LOGITS
    -bottom
    0.10
     inspired
    0.10
    atically
    0.09
     Hir
    0.09
    alue
    0.09
    geh
    0.09
     Hick
    0.09
    oky
    0.09
    arker
    0.09
    aname
    0.09
    Activations Density 0.001%

    No Known Activations