© 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. 233
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and specific tokens

    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
     accordingly
    -0.10
     otherwise
    -0.09
     konk
    -0.08
     sane
    -0.07
    ervations
    -0.07
     afterward
    -0.07
     additional
    -0.07
     echoing
    -0.07
    /↵↵
    -0.07
    以
    -0.07
    POSITIVE LOGITS
     zwar
    0.11
     sleeper
    0.09
    uw
    0.09
     Wan
    0.09
    brit
    0.09
     charms
    0.08
    !!)↵
    0.08
    .PR
    0.08
    .Today
    0.08
    Rpc
    0.08
    Activations Density 0.518%

    No Known Activations