© 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. 1769
    Prev
    Next
    INDEX
    Explanations

    r-start words and abbreviations

    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
    /right
    -0.13
    -Russian
    -0.11
    _r
    -0.11
     rice
    -0.11
     reasoning
    -0.10
     rubber
    -0.10
    irst
    -0.10
    usi
    -0.10
     rigid
    -0.09
     racket
    -0.09
    POSITIVE LOGITS
    mond
    0.14
    onda
    0.11
    allo
    0.10
    ä½ķ
    0.10
    aldo
    0.09
    ationally
    0.09
    neck
    0.09
    iem
    0.09
    dish
    0.09
    umat
    0.09
    Activations Density 3.404%

    No Known Activations