© 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. 1420
    Prev
    Next
    INDEX
    Explanations

    .

    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
    grily
    -0.27
     Clintons
    -0.25
     blackColor
    -0.25
     strncmp
    -0.25
    åħļçļĦåįģ
    -0.23
    ä¸Ģ个èģĮä¸ļ
    -0.23
     misunder
    -0.23
     "/");↵
    -0.23
    Lastly
    -0.22
    æ¡Ĩæŀ¶åįıè®®
    -0.22
    POSITIVE LOGITS
     ãĥĪãĥ©
    0.26
    .ToShort
    0.24
    iferay
    0.24
    -alist
    0.23
    pesan
    0.23
    ={['
    0.22
    responseData
    0.22
     дело
    0.22
    ï¼ģ');↵
    0.21
     And
    0.21
    Activations Density 2.452%

    No Known Activations