© 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. 4152
    Prev
    Next
    INDEX
    Explanations

    mathematical syntax and logic

    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
    uffed
    -0.07
     Pole
    -0.07
     scar
    -0.07
     Correspond
    -0.07
    া
    -0.06
    teacher
    -0.06
    Grammar
    -0.06
    olar
    -0.06
    enic
    -0.06
    osit
    -0.06
    POSITIVE LOGITS
    omp
    0.12
    PageIndex
    0.11
    ansa
    0.10
    dden
    0.10
    -extra
    0.10
    LONG
    0.10
     trench
    0.10
    mall
    0.10
    -prev
    0.10
    /star
    0.09
    Activations Density 0.026%

    No Known Activations