© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8766
    Prev
    Next
    INDEX
    Explanations

    October dates

    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
    Negative Logits
    acs
    -0.07
     Caldwell
    -0.07
    .sdk
    -0.07
    iva
    -0.07
    rier
    -0.07
    ac
    -0.07
     Shel
    -0.07
     Kramer
    -0.06
     congest
    -0.06
    ustr
    -0.06
    POSITIVE LOGITS
    аз
    0.10
    hana
    0.10
    обÑĢаÐ
    0.10
    dee
    0.10
    avo
    0.10
    olson
    0.09
    });↵↵↵↵
    0.09
     hybrid
    0.09
     oct
    0.09
     ali
    0.09
    Activations Density 0.198%

    No Known Activations