© 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. 1395
    Prev
    Next
    INDEX
    Explanations

    this

    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
    1
    -0.32
    2
    -0.29
    4
    -0.28
    5
    -0.27
    3
    -0.27
    9
    -0.26
    7
    -0.26
    8
    -0.26
    6
    -0.25
    egasus
    -0.25
    POSITIVE LOGITS
     èĭ¥è¦ģ
    0.42
     particular
    0.40
    ﹤
    0.35
     ×Ķ×ķ×ĵ
    0.34
    æĢ§ä»·
    0.33
    åľ¨è¿ĩ渡
    0.33
    ä¸ĭéĿ¢æĺ¯å°ı
    0.32
    大大å°ı
    0.32
    ä½Ĩä¸įéĻIJ
    0.31
    åľ¨çݩ家
    0.31
    Activations Density 0.893%

    No Known Activations