© 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. 789
    Prev
    Next
    INDEX
    Explanations

    components typically followed by which

    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
    [];č↵
    -0.11
    /people
    -0.11
     onwards
    -0.11
    [sizeof
    -0.11
    -0.11
    /users
    -0.10
     Misc
    -0.10
    avery
    -0.10
    swith
    -0.10
    FontSize
    -0.10
    POSITIVE LOGITS
    -like
    0.14
     consisting
    0.12
     called
    0.11
     composed
    0.11
     which
    0.11
    -type
    0.11
     aka
    0.09
     developed
    0.09
     that
    0.08
    /b
    0.08
    Activations Density 4.263%

    No Known Activations