© 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. 54194
    Prev
    Next
    INDEX
    Explanations

    moderately, repeat, round, test, perfect, table, xyz

    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
     final
    -0.11
     Ultimate
    -0.11
     Final
    -0.10
     Lastly
    -0.09
    bish
    -0.09
    zman
    -0.09
     finally
    -0.09
    pez
    -0.09
     ultimate
    -0.08
    -final
    -0.08
    POSITIVE LOGITS
     Moder
    0.09
    Moder
    0.09
     carve
    0.09
     moderately
    0.09
    Repeat
    0.08
    ura
    0.08
     Sto
    0.08
     Moderate
    0.08
    eat
    0.08
     isArray
    0.08
    Activations Density 0.048%

    No Known Activations