© 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. 929
    Prev
    Next
    INDEX
    Explanations

    399 or 39

    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
    rices
    -0.10
    lingen
    -0.10
    lie
    -0.10
    atz
    -0.10
    raries
    -0.10
    त
    -0.09
    itious
    -0.09
    al
    -0.09
    ulia
    -0.09
    argo
    -0.09
    POSITIVE LOGITS
        ↵    ↵
    0.11
    ic
    0.11
    icy
    0.10
        ↵    ↵    ↵
    0.08
    ably
    0.08
    ball
    0.08
    ¿
    0.08
    ued
    0.08
    иÑĩ
    0.08
    ãĤį
    0.08
    Activations Density 3.271%

    No Known Activations