© 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. 607
    Prev
    Next
    INDEX
    Explanations

    stationery, parkinson, cart abandonment

    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
    -0.14
    ely
    -0.13
    ently
    -0.10
    egr
    -0.10
    ibly
    -0.10
    -Israel
    -0.10
    ELY
    -0.09
    		↵		↵
    -0.09
    Ñİ
    -0.08
    ible
    -0.08
    POSITIVE LOGITS
    Ñı
    0.11
    house
    0.09
    oons
    0.09
    Ñıем
    0.09
    ruptcy
    0.09
    eros
    0.09
    pile
    0.09
    cloth
    0.09
    manship
    0.09
    keeper
    0.09
    Activations Density 5.917%

    No Known Activations