© 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. 58242
    Prev
    Next
    INDEX
    Explanations

    font size values

    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
    orate
    -0.13
    eton
    -0.11
    /editor
    -0.10
     Woods
    -0.10
    aurus
    -0.09
    lee
    -0.09
    liers
    -0.09
    bia
    -0.09
    positor
    -0.09
     доÑģÑĤ
    -0.09
    POSITIVE LOGITS
     ripe
    0.09
     wrong
    0.08
     fly
    0.07
     moth
    0.07
     ph
    0.07
    asin
    0.07
     Paige
    0.07
    aan
    0.07
     Burns
    0.07
    wrong
    0.07
    Activations Density 0.002%

    No Known Activations