© 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. 56226
    Prev
    Next
    INDEX
    Explanations

    accessing list/array elements

    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
    inger
    -0.11
     TRE
    -0.09
    IGH
    -0.09
     seed
    -0.09
     Jah
    -0.09
     trait
    -0.09
    1
    -0.09
    .k
    -0.09
    Advertisement
    -0.09
     joe
    -0.09
    POSITIVE LOGITS
    dae
    0.08
    jom
    0.08
    onet
    0.08
    \',
    0.07
    bat
    0.07
    .herokuapp
    0.07
     Orient
    0.07
    [
    0.07
    .off
    0.07
    uela
    0.07
    Activations Density 0.009%

    No Known Activations