© 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. 330
    Prev
    Next
    INDEX
    Explanations

    level of X

    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
    ÑĤе
    -0.10
    {}",
    -0.09
    Ñģки
    -0.09
     kend
    -0.08
    ystate
    -0.08
     notions
    -0.08
     seri
    -0.08
    ä¸Ģ个
    -0.08
    ifo
    -0.08
    ensen
    -0.08
    POSITIVE LOGITS
    0.12
     information
    0.10
     forward
    0.09
     excellence
    0.09
     “
    0.09
     functionality
    0.09
     Excellence
    0.09
     abstraction
    0.09
     aw
    0.09
    è¯Ŀ
    0.09
    Activations Density 1.597%

    No Known Activations