© 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. 58289
    Prev
    Next
    INDEX
    Explanations

    located in / from

    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
    uden
    -0.08
    olla
    -0.07
     simultaneously
    -0.07
    ¥
    -0.07
    MAR
    -0.07
    iates
    -0.07
    ÙĪر
    -0.06
    ients
    -0.06
     annually
    -0.06
     consistently
    -0.06
    POSITIVE LOGITS
     seventeen
    0.11
     thirteen
    0.11
     various
    0.11
     Heath
    0.11
     eighteen
    0.11
     eleven
    0.11
    çīĪ
    0.10
    /--
    0.10
    igli
    0.10
     fifteen
    0.10
    Activations Density 0.092%

    No Known Activations