© 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. 933
    Prev
    Next
    INDEX
    Explanations

    code declarations

    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
    -scenes
    -0.25
     seiz
    -0.25
    -toggler
    -0.23
    è¦ģçŁ¥éģĵ
    -0.23
    )(((
    -0.23
     Noticed
    -0.23
    anzi
    -0.22
     misd
    -0.22
     disadv
    -0.21
     noe
    -0.21
    POSITIVE LOGITS
    :;↵
    0.27
    ÄĴ
    0.27
    ï¼ģ');↵
    0.27
    âŀ¢
    0.25
    (strtolower
    0.25
    åľ¨è¿ĩ渡
    0.25
    ðŁļ©
    0.24
    该游æĪı
    0.23
    佶
    0.23
     BuzzFeed
    0.23
    Activations Density 0.942%

    No Known Activations