© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3529
    Prev
    Next
    INDEX
    Explanations

    `groupId` tag and namespace

    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
    ses
    -0.09
    jan
    -0.09
    atted
    -0.09
    ки
    -0.07
     dou
    -0.07
    ryn
    -0.07
    edar
    -0.07
    langs
    -0.07
    led
    -0.07
    ("'",
    -0.07
    POSITIVE LOGITS
     Bosch
    0.11
    arb
    0.10
    -extra
    0.09
    /company
    0.09
    0.09
     sco
    0.09
    -info
    0.09
     Namespace
    0.09
    upo
    0.09
    -summary
    0.09
    Activations Density 0.135%

    No Known Activations