© 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. 61627
    Prev
    Next
    INDEX
    Explanations

    read more

    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
    ually
    -0.10
    ousse
    -0.10
    ially
    -0.10
    cke
    -0.10
    /comments
    -0.09
    ses
    -0.09
    ively
    -0.09
     Pending
    -0.09
    (JFrame
    -0.09
    (er
    -0.09
    POSITIVE LOGITS
     unintended
    0.08
    quia
    0.07
    eder
    0.07
    elp
    0.07
    asm
    0.07
    tax
    0.07
    inos
    0.07
    inger
    0.07
     hall
    0.07
     Sachs
    0.06
    Activations Density 0.019%

    No Known Activations