© 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. 56038
    Prev
    Next
    INDEX
    Explanations

    royalty names followed by Roman numerals

    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
     decrement
    -0.09
     Consult
    -0.09
     persecution
    -0.08
     Lotto
    -0.08
     Lesser
    -0.08
    ersist
    -0.08
    TeX
    -0.08
    adro
    -0.08
     Pics
    -0.08
     Onion
    -0.08
    POSITIVE LOGITS
     professionally
    0.09
     II
    0.09
     vel
    0.08
     III
    0.08
    igin
    0.08
     mirror
    0.08
    II
    0.08
     professional
    0.08
     previously
    0.08
     del
    0.07
    Activations Density 0.024%

    No Known Activations