© 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. 1107
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions

    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
    uxtap
    -0.23
    åħīèį£
    -0.23
    åijĬè¯ī大家
    -0.22
    ﹤
    -0.22
    -strokes
    -0.22
    SuccessListener
    -0.22
     nostalg
    -0.21
    åľ¨éĩĮéĿ¢
    -0.21
    abcdefghijkl
    -0.21
     hubby
    -0.21
    POSITIVE LOGITS
    交å¾Ģ
    0.28
    ç½ijé¦ĸ页
    0.26
    ä¸ī大éĺ¶æ®µ
    0.26
     recip
    0.26
     friendship
    0.25
    缸å¤Ħ
    0.23
     lowes
    0.23
    èĶ¸
    0.23
     aprox
    0.22
    èµ°è¿ij
    0.22
    Activations Density 3.178%

    No Known Activations