© 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. 4405
    Prev
    Next
    INDEX
    Explanations

    Mat names

    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
     Hir
    -0.11
    awks
    -0.10
    leton
    -0.10
     contra
    -0.10
     Pruitt
    -0.09
    iful
    -0.09
     specialized
    -0.08
     Prom
    -0.08
     informat
    -0.08
    uras
    -0.08
    POSITIVE LOGITS
    yas
    0.11
    /mat
    0.11
    rices
    0.09
    inson
    0.09
    sonian
    0.08
    uration
    0.08
     bald
    0.08
    wie
    0.08
    ina
    0.08
    bsite
    0.08
    Activations Density 0.198%

    No Known Activations