© 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. 56383
    Prev
    Next
    INDEX
    Explanations

    Red Hat, Inc

    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
     lt
    -0.10
    otti
    -0.10
    alto
    -0.09
    Ùī
    -0.09
    ÙĦÙī
    -0.09
     allure
    -0.09
    tg
    -0.09
    erland
    -0.09
     sanitize
    -0.09
    aat
    -0.09
    POSITIVE LOGITS
     Nach
    0.08
    ape
    0.08
    inel
    0.07
     Borders
    0.07
    GRA
    0.07
     Bac
    0.07
     Barnes
    0.07
    avin
    0.07
    asto
    0.07
    strap
    0.07
    Activations Density 0.003%

    No Known Activations