© 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. 58059
    Prev
    Next
    INDEX
    Explanations

    court filings and legal documents

    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
    cred
    -0.10
     créd
    -0.10
    gens
    -0.10
    opsis
    -0.09
     Carousel
    -0.09
    illery
    -0.09
     sach
    -0.09
    uries
    -0.09
    ={{
    -0.09
    cesso
    -0.09
    POSITIVE LOGITS
    hb
    0.09
     repeat
    0.08
    ity
    0.07
     ventured
    0.07
     rue
    0.07
     stap
    0.07
     denounced
    0.07
     Scha
    0.07
    og
    0.07
    iant
    0.07
    Activations Density 0.001%

    No Known Activations