© 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
    2. Olmo-3-1025-7B
    3. 16-RES-MATRYOSHKA-65K
    4. 3440
    Prev
    Next
    INDEX
    Explanations

    interior space

    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
     ..↵↵
    -0.11
    -END
    -0.11
    ][_
    -0.11
    -With
    -0.11
    ...↵↵↵
    -0.11
    !!)↵
    -0.11
    ->↵
    -0.10
    ..'
    -0.10
     ..↵
    -0.10
    .Ac
    -0.10
    POSITIVE LOGITS
    .
    0.17
    ;
    0.16
     while
    0.15
    ,
    0.14
    .↵↵
    0.14
     without
    0.13
     when
    0.13
     before
    0.13
     with
    0.13
     during
    0.13
    Activations Density 1.297%

    No Known Activations