© 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. 2758
    Prev
    Next
    INDEX
    Explanations

    references and citations

    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
     unjust
    -0.08
     Hunts
    -0.07
    alian
    -0.07
     downstairs
    -0.06
    ica
    -0.06
     Ace
    -0.06
     Flint
    -0.06
     proving
    -0.06
     Fourth
    -0.06
     dim
    -0.06
    POSITIVE LOGITS
    elry
    0.12
    lick
    0.11
    gow
    0.10
    VILLE
    0.10
    %X
    0.10
     Bever
    0.10
    @student
    0.10
    checker
    0.10
     CreateTable
    0.10
    outu
    0.09
    Activations Density 0.048%

    No Known Activations