© 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. 600
    Prev
    Next
    INDEX
    Explanations

    research and investigation

    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
    åľ¨çݩ家ä¸Ń
    -0.24
    åĽłä¸ºä»ĸ
    -0.23
    ccording
    -0.23
    AppComponent
    -0.22
    },{↵
    -0.22
    ;if
    -0.22
    åľ¨ä»ĸçļĦ
    -0.21
    )↵↵↵↵↵↵↵↵
    -0.21
    以åħ¶
    -0.21
    åİŁåĽłä¹ĭä¸Ģ
    -0.21
    POSITIVE LOGITS
     there
    0.48
     we
    0.44
    there
    0.38
    æĪij们
    0.33
    ,
    0.32
     it
    0.31
    ï¼Į
    0.30
     they
    0.28
     мÑĭ
    0.28
     you
    0.28
    Activations Density 3.035%

    No Known Activations