© 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. 1127
    Prev
    Next
    INDEX
    Explanations

    script tags and javascript

    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
    ele
    -0.08
     architect
    -0.08
    eat
    -0.08
    anium
    -0.08
     Hamp
    -0.08
    atab
    -0.08
     annunci
    -0.08
    avr
    -0.08
    ty
    -0.08
     Fat
    -0.07
    POSITIVE LOGITS
    (jQuery
    0.10
    unj
    0.10
     kindergarten
    0.10
    coni
    0.10
    upp
    0.09
    /j
    0.09
    Ñģли
    0.09
     kindly
    0.09
    ous
    0.09
    (JS
    0.09
    Activations Density 1.606%

    No Known Activations