© 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. 483
    Prev
    Next
    INDEX
    Explanations

    user input fields

    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
    empo
    -0.08
     embraces
    -0.08
     Eval
    -0.08
    .Diagnostics
    -0.08
     Pager
    -0.08
     bookmarks
    -0.08
     Victor
    -0.08
    MED
    -0.08
     publishes
    -0.08
    RSS
    -0.08
    POSITIVE LOGITS
     input
    0.13
     inputs
    0.12
     Input
    0.12
    Input
    0.12
     fields
    0.12
     prompts
    0.11
    _input
    0.11
    input
    0.11
    -input
    0.11
     Fields
    0.10
    Activations Density 1.928%

    No Known Activations