© 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. 2814
    Prev
    Next
    INDEX
    Explanations

    en + following word

    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
    uary
    -0.09
    itra
    -0.09
     Gate
    -0.09
    orie
    -0.09
    ites
    -0.09
    >[]
    -0.09
    ikes
    -0.08
    oras
    -0.08
    ella
    -0.08
    ally
    -0.08
    POSITIVE LOGITS
    ment
    0.13
    sembles
    0.10
    ame
    0.09
    ments
    0.09
    kid
    0.09
    aging
    0.09
    -us
    0.09
    ainment
    0.09
    agement
    0.08
     casc
    0.08
    Activations Density 0.212%

    No Known Activations