© 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. 553
    Prev
    Next
    INDEX
    Explanations

    `div`, `gui`, `gt`, `dt` prefixes

    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
    áŀ¶
    -0.10
     ARISING
    -0.10
    idak
    -0.10
    ör
    -0.10
    .,↵
    -0.10
    egov
    -0.10
     sweetheart
    -0.10
     Beaut
    -0.10
    697
    -0.09
     panorama
    -0.09
    POSITIVE LOGITS
     Bahamas
    0.07
    ews
    0.06
    REM
    0.06
    /document
    0.06
    Tokenizer
    0.06
    -utils
    0.06
    -archive
    0.06
    č↵	č↵
    0.06
    ElementsBy
    0.06
    -exclusive
    0.06
    Activations Density 1.166%

    No Known Activations