© 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. 57078
    Prev
    Next
    INDEX
    Explanations

    date and code separators

    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
     Calif
    -0.07
     Flyers
    -0.07
    ...
    -0.07
    :Any
    -0.06
     sounding
    -0.06
    olding
    -0.06
     flying
    -0.06
    -addons
    -0.06
    illet
    -0.06
    bew
    -0.06
    POSITIVE LOGITS
    :\/\/
    0.12
     ^↵
    0.12
     ?↵
    0.11
    **↵
    0.10
    *↵
    0.10
     Painter
    0.10
    __↵
    0.10
    !↵
    0.09
    apot
    0.09
     !↵
    0.09
    Activations Density 0.025%

    No Known Activations