© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1211
    Prev
    Next
    INDEX
    Explanations

    research papers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :params
    -0.28
    )__
    -0.23
    éķŀ
    -0.23
    /Dk
    -0.22
    UnderTest
    -0.22
    æĭľå¸ĪåѦ
    -0.22
    *Math
    -0.21
    ropri
    -0.21
    :"-"`↵
    -0.21
    :normal
    -0.21
    POSITIVE LOGITS
     studies
    0.35
     published
    0.34
     literature
    0.29
     scattered
    0.27
    published
    0.26
     reference
    0.26
     litter
    0.25
     publications
    0.25
     references
    0.25
    åĽ½åĨħå¤ĸ
    0.25
    Activations Density 2.944%

    No Known Activations