© 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. 54517
    Prev
    Next
    INDEX
    Explanations

    description keyword

    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
     Baghd
    -0.09
    fried
    -0.09
    ople
    -0.09
    267
    -0.08
     summary
    -0.08
     preference
    -0.08
    incipal
    -0.08
    abis
    -0.08
     trium
    -0.08
    ather
    -0.08
    POSITIVE LOGITS
     crack
    0.08
    lauf
    0.08
     Pom
    0.08
     Geg
    0.07
     dou
    0.07
     Compet
    0.07
     rival
    0.07
    áŁĴáŀ
    0.07
    jon
    0.07
     даннÑĭÑħ
    0.07
    Activations Density 0.043%

    No Known Activations