© 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. 3313
    Prev
    Next
    INDEX
    Explanations

    ulinary

    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
    bor
    -0.09
    ey
    -0.09
    upp
    -0.09
     Curtain
    -0.08
     Mafia
    -0.08
    coins
    -0.08
     Apr
    -0.08
     iv
    -0.08
    ighton
    -0.08
    iqu
    -0.08
    POSITIVE LOGITS
     Mang
    0.08
    uct
    0.08
    enas
    0.08
    /#
    0.08
    pref
    0.08
     Robertson
    0.08
     ====
    0.08
     Patron
    0.08
    erver
    0.08
    /content
    0.08
    Activations Density 0.066%

    No Known Activations