© 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. 2632
    Prev
    Next
    INDEX
    Explanations

    famous biographies

    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
     OPTIONAL
    -0.11
     peripheral
    -0.09
     slightly
    -0.09
     briefly
    -0.08
    sit
    -0.08
     elong
    -0.08
     shine
    -0.08
     scratches
    -0.08
     petty
    -0.08
     eget
    -0.07
    POSITIVE LOGITS
    argo
    0.11
     Nobel
    0.10
     famously
    0.10
     Cruc
    0.09
     intentionally
    0.09
    hausen
    0.09
     famous
    0.09
     hilar
    0.08
    embro
    0.08
     inventive
    0.08
    Activations Density 0.682%

    No Known Activations