© 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. 3418
    Prev
    Next
    INDEX
    Explanations

    person names dates (year)

    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
     lean
    -0.09
     lev
    -0.08
     ruled
    -0.07
     grandmother
    -0.07
    oge
    -0.07
     sext
    -0.07
    dda
    -0.07
    251
    -0.07
     leaning
    -0.07
    ank
    -0.06
    POSITIVE LOGITS
    ipel
    0.10
    ù
    0.10
    EDI
    0.10
    thumbs
    0.09
    omed
    0.09
    urg
    0.09
    _again
    0.09
    -Sh
    0.09
    ager
    0.09
    Reload
    0.09
    Activations Density 0.144%

    No Known Activations