© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55683
    Prev
    Next
    INDEX
    Explanations

    push or call

    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
    wij
    -0.09
    163
    -0.08
    ett
    -0.08
     Kem
    -0.08
     amo
    -0.07
    ande
    -0.07
    /Form
    -0.07
    LAN
    -0.07
    ystone
    -0.07
    -cond
    -0.07
    POSITIVE LOGITS
    pile
    0.10
    Į¨
    0.09
    allis
    0.09
    ically
    0.09
    atis
    0.09
     Merry
    0.09
     sez
    0.09
     Motors
    0.09
    ikal
    0.08
     Herald
    0.08
    Activations Density 0.001%

    No Known Activations