© 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. 54953
    Prev
    Next
    INDEX
    Explanations

    aged, bourne, shore

    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
     Reactive
    -0.10
    oo
    -0.09
    gow
    -0.09
     Interr
    -0.09
    ÑģÑı
    -0.09
    ingly
    -0.09
    kaar
    -0.09
    олÑĮзов
    -0.09
    ervo
    -0.09
    ecom
    -0.09
    POSITIVE LOGITS
    aged
    0.10
    hurst
    0.10
    ic
    0.09
    ager
    0.09
    aine
    0.09
    al
    0.08
    bourne
    0.08
    rc
    0.08
    shore
    0.08
    à¸Ľ
    0.08
    Activations Density 0.010%

    No Known Activations