© 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. 55852
    Prev
    Next
    INDEX
    Explanations

    passageways, staff, legends

    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
    "is
    -0.09
     opts
    -0.09
    Ц
    -0.08
    EIF
    -0.08
    دÙĩ
    -0.08
    Ñĥг
    -0.08
    \\/
    -0.08
     mandate
    -0.08
     Kid
    -0.08
    ket
    -0.08
    POSITIVE LOGITS
    elah
    0.09
     cropped
    0.09
     blanket
    0.09
     preceded
    0.09
     govern
    0.08
    iosa
    0.08
     governed
    0.08
     dot
    0.08
     replace
    0.08
    helm
    0.08
    Activations Density 0.148%

    No Known Activations