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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1802
    Prev
    Next
    INDEX
    Explanations

    document structure

    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
    é¢Ģ
    -0.20
     whiteColor
    -0.20
    迨
    -0.19
    é«ĺéĽĦ
    -0.18
    çľ·
    -0.18
    áºŃn
    -0.18
    æľĿ
    -0.18
    ç¦ļ
    -0.18
    åľ¨æĦı
    -0.18
    è¶ģ
    -0.18
    POSITIVE LOGITS
     GdaÅĦsk
    0.22
    onents
    0.20
     lucr
    0.20
    æģĵ
    0.20
    åĶ¤
    0.19
    åij¼ãģ°ãĤĮ
    0.19
    mouseleave
    0.19
     ÑĦай
    0.19
    hiên
    0.19
    SWG
    0.19
    Activations Density 0.001%

    No Known Activations