© 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. 1539
    Prev
    Next
    INDEX
    Explanations

    domain suffixes

    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
    /rfc
    -0.10
    /commons
    -0.09
    /tutorial
    -0.09
    =end
    -0.09
    /mainwindow
    -0.09
    /messages
    -0.09
     Mar
    -0.09
    .php
    -0.09
    yme
    -0.09
    ?family
    -0.09
    POSITIVE LOGITS
    .au
    0.19
    .br
    0.16
    /~
    0.14
    lify
    0.14
    .uk
    0.13
    .cn
    0.13
    .mx
    0.12
    .ua
    0.12
    .il
    0.11
    .tr
    0.11
    Activations Density 0.568%

    No Known Activations