© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2241
    Prev
    Next
    INDEX
    Explanations

    mathematical structures and decomposition

    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
    ooled
    -0.09
    ainted
    -0.09
    Preview
    -0.09
     capped
    -0.09
     interp
    -0.09
    yg
    -0.08
     Dutch
    -0.08
     heaven
    -0.08
    lest
    -0.08
    ichel
    -0.08
    POSITIVE LOGITS
     decomposition
    0.13
     Decom
    0.12
     decom
    0.11
     Pit
    0.08
     UNIQUE
    0.08
     Races
    0.08
    .unique
    0.08
     dess
    0.08
     inevitable
    0.07
     Batter
    0.07
    Activations Density 0.128%

    No Known Activations