© 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. 2008
    Prev
    Next
    INDEX
    Explanations

    features and characteristics

    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
    oft
    -0.09
     Worldwide
    -0.08
    大å°ı
    -0.08
    izer
    -0.07
    504
    -0.07
    .lookup
    -0.07
    pic
    -0.07
     dak
    -0.07
    /nav
    -0.07
     containing
    -0.07
    POSITIVE LOGITS
    /features
    0.21
     enumerated
    0.17
    /questions
    0.15
     listed
    0.14
    /issues
    0.14
    listed
    0.14
    /problems
    0.14
     features
    0.14
     pertaining
    0.14
     including
    0.13
    Activations Density 3.098%

    No Known Activations