© 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. 57874
    Prev
    Next
    INDEX
    Explanations

    data, tables, templates, cases, history, events, registry, styles

    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
    æİĴ
    -0.10
    abei
    -0.10
    acha
    -0.10
     rab
    -0.09
    configure
    -0.09
    ISING
    -0.09
    .si
    -0.09
    errat
    -0.09
    .inst
    -0.09
    aso
    -0.09
    POSITIVE LOGITS
     squirt
    0.08
     Cru
    0.07
     enrichment
    0.07
     Offline
    0.07
    ahl
    0.07
     offline
    0.07
    æł¸
    0.07
    /**/*.
    0.07
     INTO
    0.07
    uf
    0.06
    Activations Density 0.122%

    No Known Activations