© 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. 54534
    Prev
    Next
    INDEX
    Explanations

    containing or comprising something

    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
     Direct
    -0.09
     separate
    -0.09
     direct
    -0.09
    amer
    -0.09
    GER
    -0.09
     Dire
    -0.08
    andas
    -0.08
     stock
    -0.08
     pseud
    -0.08
     charms
    -0.08
    POSITIVE LOGITS
    ittal
    0.08
    amins
    0.08
    orth
    0.08
     FRE
    0.08
    /Application
    0.08
     ammonia
    0.08
    ni
    0.08
     Dit
    0.08
     fantas
    0.08
    ramework
    0.08
    Activations Density 0.057%

    No Known Activations