© 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. 54707
    Prev
    Next
    INDEX
    Explanations

    wheel or pilot

    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
    ibri
    -0.11
     designs
    -0.10
     Asc
    -0.10
    bdb
    -0.10
    lip
    -0.09
     convo
    -0.09
    (↵↵
    -0.09
    haar
    -0.09
    GEST
    -0.09
    indr
    -0.09
    POSITIVE LOGITS
    ait
    0.09
    åº
    0.08
    mere
    0.08
     Rod
    0.07
    desk
    0.07
    /licenses
    0.07
    sea
    0.07
     hut
    0.07
    aea
    0.07
     unw
    0.07
    Activations Density 0.027%

    No Known Activations