© 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. 3518
    Prev
    Next
    INDEX
    Explanations

    this context/case/manner

    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
     dated
    -0.09
    ights
    -0.08
     energies
    -0.07
    .|
    -0.07
    Gab
    -0.07
     travelled
    -0.07
     poco
    -0.07
    ilities
    -0.07
    aria
    -0.07
     traveled
    -0.07
    POSITIVE LOGITS
     way
    0.11
     regard
    0.11
     respect
    0.10
     case
    0.10
     reason
    0.10
     Wolfe
    0.10
     basis
    0.10
     Rank
    0.09
     regards
    0.09
    rika
    0.09
    Activations Density 0.111%

    No Known Activations