© 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. 1974
    Prev
    Next
    INDEX
    Explanations

    numbers or "Jared Allen"

    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
    uate
    -0.10
    ful
    -0.10
    ast
    -0.09
    iff
    -0.09
    uds
    -0.08
    ãģ¦
    -0.08
    fully
    -0.08
    led
    -0.08
    les
    -0.08
    ÑĨи
    -0.08
    POSITIVE LOGITS
    ÑĤÑĮ
    0.11
    rance
    0.11
    olu
    0.10
    ness
    0.10
    enheim
    0.10
    ков
    0.10
     )),↵
    0.09
    oire
    0.09
    rious
    0.09
    ships
    0.09
    Activations Density 3.839%

    No Known Activations