© 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. 3170
    Prev
    Next
    INDEX
    Explanations

    `bytes` and `io` imports

    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
    ather
    -0.09
    olg
    -0.09
     Reload
    -0.09
     Advent
    -0.08
    langs
    -0.08
    adin
    -0.08
     unint
    -0.08
    474
    -0.08
     pocket
    -0.08
    anel
    -0.08
    POSITIVE LOGITS
    rial
    0.08
    /ioutil
    0.08
    usercontent
    0.08
     tá»
    0.08
    TY
    0.08
    ially
    0.08
    aji
    0.08
    owie
    0.08
    urtles
    0.07
    GetValue
    0.07
    Activations Density 0.013%

    No Known Activations