© 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. 663
    Prev
    Next
    INDEX
    Explanations

    is a definition or description

    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
    ses
    -0.10
     outright
    -0.09
     wished
    -0.09
     ensuing
    -0.09
     aforementioned
    -0.09
     aloud
    -0.08
    conditionally
    -0.08
     thereof
    -0.08
     unsuccessfully
    -0.08
    br
    -0.08
    POSITIVE LOGITS
     also
    0.18
     mainly
    0.13
     primarily
    0.13
    :')
    0.12
     divided
    0.12
     predomin
    0.11
    :")
    0.11
     especially
    0.11
     typically
    0.10
    also
    0.10
    Activations Density 3.044%

    No Known Activations