© 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. 1637
    Prev
    Next
    INDEX
    Explanations

    technical terms or labels

    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
    -0.15
    ings
    -0.14
    sets
    -0.14
    lessly
    -0.14
    ctr
    -0.13
    book
    -0.13
    wards
    -0.13
    Ùij
    -0.12
    usterity
    -0.12
     byteArray
    -0.12
    POSITIVE LOGITS
    hip
    0.14
    ity
    0.13
    ally
    0.13
    al
    0.13
    cies
    0.13
    ized
    0.12
    e
    0.12
    ALLY
    0.12
    mente
    0.10
    ization
    0.10
    Activations Density 13.446%

    No Known Activations