© 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. 57178
    Prev
    Next
    INDEX
    Explanations

    authors reporting research

    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
     spo
    -0.09
    DEX
    -0.09
    -ac
    -0.09
    atra
    -0.08
     sid
    -0.08
    uns
    -0.08
     Abr
    -0.08
    oz
    -0.08
    azer
    -0.08
    asher
    -0.08
    POSITIVE LOGITS
    .TryParse
    0.09
    iets
    0.09
    hift
    0.09
    anko
    0.09
    以ä¸Ĭ
    0.09
    burg
    0.09
    -country
    0.09
     bean
    0.09
    richt
    0.09
     Bean
    0.08
    Activations Density 0.008%

    No Known Activations