© 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. 54242
    Prev
    Next
    INDEX
    Explanations

    subprocess and os.popen

    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
     enclosed
    -0.09
     Fight
    -0.08
     umb
    -0.08
    vang
    -0.08
    ynos
    -0.08
    .$.
    -0.08
    dl
    -0.08
     seri
    -0.08
    tele
    -0.08
     Fool
    -0.08
    POSITIVE LOGITS
    imately
    0.09
     viewpoint
    0.09
    ardin
    0.08
    ishly
    0.08
    board
    0.08
    favor
    0.08
     viewpoints
    0.08
    cobra
    0.08
     thumbs
    0.08
    allen
    0.08
    Activations Density 0.012%

    No Known Activations