© 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. 2031
    Prev
    Next
    INDEX
    Explanations

    person in social context

    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
     wherever
    -0.12
    warts
    -0.10
     everywhere
    -0.10
     Paperback
    -0.10
     Kardash
    -0.10
     either
    -0.10
    REA
    -0.10
     strives
    -0.10
     whenever
    -0.10
    pard
    -0.10
    POSITIVE LOGITS
     recently
    0.16
     unrelated
    0.14
     accidentally
    0.14
     (?)
    0.12
     nearby
    0.12
     someone
    0.11
     another
    0.11
     somewhere
    0.11
     called
    0.11
     mistakenly
    0.11
    Activations Density 3.929%

    No Known Activations