© 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. 55907
    Prev
    Next
    INDEX
    Explanations

    understanding of how

    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
    ther
    -0.09
     æŃ
    -0.08
     specifically
    -0.08
     voc
    -0.08
    vin
    -0.08
    unks
    -0.08
    uations
    -0.08
    uel
    -0.08
     violated
    -0.08
    ustr
    -0.08
    POSITIVE LOGITS
    stown
    0.10
    qm
    0.08
    hei
    0.08
    ete
    0.08
     how
    0.08
    exam
    0.08
    iciary
    0.08
     themselves
    0.08
    kur
    0.07
    allo
    0.07
    Activations Density 0.095%

    No Known Activations