© 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. 583
    Prev
    Next
    INDEX
    Explanations

    introducing examples or contrast

    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
    ;b
    -0.13
    ;/*
    -0.12
    ;k
    -0.12
     sondern
    -0.12
    ):(
    -0.11
    ;z
    -0.11
    )=='
    -0.11
    .;↵
    -0.10
    ;a
    -0.10
    {}.
    -0.10
    POSITIVE LOGITS
    ,
    0.27
    ,↵
    0.12
    ,the
    0.12
    ,.
    0.12
    ,↵↵
    0.12
    ,\↵
    0.12
    ,âĢ¦↵↵
    0.11
    ,č↵č↵
    0.11
    ,**
    0.10
    ,č↵
    0.10
    Activations Density 1.146%

    No Known Activations