© 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. 2195
    Prev
    Next
    INDEX
    Explanations

    simplify fractions and exponents

    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
     tant
    -0.09
    hone
    -0.09
    gli
    -0.09
    arta
    -0.08
     malt
    -0.08
     Devils
    -0.08
    mal
    -0.08
    ouro
    -0.08
    nof
    -0.08
     devil
    -0.08
    POSITIVE LOGITS
     alkal
    0.09
     Prompt
    0.09
    cz
    0.09
    comb
    0.08
    Prompt
    0.08
    builtin
    0.08
     prompt
    0.08
     Doming
    0.08
     Likes
    0.08
     gener
    0.08
    Activations Density 0.048%

    No Known Activations