© 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. 58430
    Prev
    Next
    INDEX
    Explanations

    buffered Reader

    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
    ienda
    -0.09
    åĢ
    -0.09
    ÑĢав
    -0.09
    ventory
    -0.09
    pane
    -0.08
    /API
    -0.08
    ';↵↵↵↵
    -0.08
    rede
    -0.08
    ses
    -0.08
    .appspot
    -0.08
    POSITIVE LOGITS
    ness
    0.08
     fr
    0.08
     quar
    0.08
    anco
    0.08
     Lamar
    0.07
    CMS
    0.07
     Bates
    0.07
    PEAR
    0.07
    rax
    0.07
    nees
    0.07
    Activations Density 0.023%

    No Known Activations