© 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. 54374
    Prev
    Next
    INDEX
    Explanations

    index initialization

    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
     Mat
    -0.08
    ney
    -0.07
     implied
    -0.07
     fores
    -0.07
     independents
    -0.06
    ê
    -0.06
    æĿ¥æºIJ
    -0.06
    urnished
    -0.06
     plausible
    -0.06
     Nose
    -0.06
    POSITIVE LOGITS
    rit
    0.10
    .findIndex
    0.10
    977
    0.09
    iod
    0.09
    rek
    0.09
    asca
    0.09
    (Log
    0.09
    IRON
    0.09
    ania
    0.09
     tally
    0.09
    Activations Density 0.009%

    No Known Activations