© 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. 4019
    Prev
    Next
    INDEX
    Explanations

    python paths

    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
     Pear
    -0.10
     offs
    -0.10
    ffen
    -0.10
    daq
    -0.10
    udo
    -0.10
    .myapplication
    -0.10
    enz
    -0.09
     Tops
    -0.09
    glich
    -0.09
     Coy
    -0.09
    POSITIVE LOGITS
    ist
    0.08
    /english
    0.07
    ŀ
    0.07
     Hann
    0.07
    char
    0.07
     Gust
    0.07
     dist
    0.07
    stown
    0.07
    isto
    0.07
     disturbance
    0.07
    Activations Density 0.043%

    No Known Activations