© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57333
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and operations

    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
     admir
    -0.11
     trov
    -0.10
     cer
    -0.10
     umbrella
    -0.10
     Sahara
    -0.10
    ombine
    -0.10
     Uhr
    -0.09
     Cav
    -0.09
     dello
    -0.09
     rival
    -0.09
    POSITIVE LOGITS
     pointing
    0.08
     (*)
    0.08
     (...)
    0.08
     chore
    0.08
    lew
    0.08
    le
    0.07
     Chore
    0.07
    browse
    0.07
    "@
    0.07
    )::
    0.07
    Activations Density 0.073%

    No Known Activations