© 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. 56857
    Prev
    Next
    INDEX
    Explanations

    1905), 40-160 microns),

    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
    asca
    -0.08
    ording
    -0.08
     Pepper
    -0.08
    dzi
    -0.07
    uesday
    -0.07
    undry
    -0.07
    isky
    -0.07
    agher
    -0.07
    ardy
    -0.07
    mar
    -0.07
    POSITIVE LOGITS
     cha
    0.09
    /issues
    0.09
     mess
    0.08
    .tsv
    0.08
     Miche
    0.08
     Trevor
    0.08
    trap
    0.08
     seniors
    0.08
     switch
    0.08
    /her
    0.08
    Activations Density 0.013%

    No Known Activations