© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 153
    Prev
    Next
    INDEX
    Explanations

    names of entities

    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
     dara
    -0.10
    ako
    -0.10
    -angular
    -0.10
     dici
    -0.09
    etz
    -0.09
    pts
    -0.09
    .§
    -0.09
    ople
    -0.09
    /Core
    -0.09
    edor
    -0.09
    POSITIVE LOGITS
     called
    0.22
     named
    0.19
     namely
    0.17
    ìĿ¸
    0.16
    called
    0.15
     olan
    0.15
     llam
    0.13
     termed
    0.13
     viz
    0.13
    ,
    0.12
    Activations Density 2.638%

    No Known Activations