© 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. 847
    Prev
    Next
    INDEX
    Explanations

    seventh circuit

    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
    y
    -0.11
    press
    -0.10
    ardo
    -0.10
    entic
    -0.10
    ured
    -0.10
    ering
    -0.10
    ary
    -0.09
    gle
    -0.09
    alty
    -0.09
    ality
    -0.09
    POSITIVE LOGITS
    .widget
    0.13
    eenth
    0.11
    th
    0.11
    /owl
    0.10
    onta
    0.10
    .SP
    0.09
    zip
    0.09
    ations
    0.09
    ÑĢам
    0.09
    otte
    0.09
    Activations Density 1.058%

    No Known Activations