© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1762
    Prev
    Next
    INDEX
    Explanations

    Yo

    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
    MMMM
    -0.10
    endar
    -0.09
    ddf
    -0.08
    اب
    -0.08
    dek
    -0.07
    lical
    -0.07
    CCCC
    -0.07
     merits
    -0.07
    ddb
    -0.07
    elong
    -0.07
    POSITIVE LOGITS
    .Download
    0.11
    ioned
    0.10
     drunken
    0.10
    odor
    0.10
    Ĺı
    0.09
    pkg
    0.09
    iov
    0.09
     createElement
    0.09
    /*!
    0.09
    isque
    0.09
    Activations Density 0.279%

    No Known Activations