© 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. 4285
    Prev
    Next
    INDEX
    Explanations

    mathematical notation fragments

    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
    itional
    -0.09
     Wak
    -0.08
     engines
    -0.08
     exploding
    -0.08
     quot
    -0.07
     hip
    -0.07
    piel
    -0.07
     fore
    -0.07
    ody
    -0.07
     passing
    -0.07
    POSITIVE LOGITS
    ades
    0.11
    atile
    0.09
    andler
    0.09
    rome
    0.09
     twists
    0.09
    orno
    0.09
    غ
    0.09
     Barn
    0.09
    agger
    0.09
     canon
    0.09
    Activations Density 0.027%

    No Known Activations