© 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. 712
    Prev
    Next
    INDEX
    Explanations

    saved options and settings

    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
    -twitter
    -0.10
    >Please
    -0.10
    checker
    -0.09
    iero
    -0.09
    /stream
    -0.09
    -Headers
    -0.09
     Posting
    -0.09
     compilers
    -0.09
    -google
    -0.09
     Jacob
    -0.09
    POSITIVE LOGITS
     settings
    0.16
     automatically
    0.15
     option
    0.15
     options
    0.14
     preset
    0.13
     saved
    0.13
     Settings
    0.13
     preview
    0.13
     your
    0.12
     automatic
    0.11
    Activations Density 3.717%

    No Known Activations