© 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. 58444
    Prev
    Next
    INDEX
    Explanations

    arithmetic expressions

    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
    yp
    -0.08
    LOGGER
    -0.08
    eq
    -0.07
     skl
    -0.07
     foregoing
    -0.07
    rag
    -0.07
     ole
    -0.07
    alte
    -0.07
    enus
    -0.07
    Gem
    -0.07
    POSITIVE LOGITS
    -contrib
    0.09
     ndarray
    0.09
     paired
    0.09
     major
    0.08
    mb
    0.08
    än
    0.08
     addict
    0.08
    entin
    0.08
    ð
    0.08
    aver
    0.08
    Activations Density 0.001%

    No Known Activations