© 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. 1047
    Prev
    Next
    INDEX
    Explanations

    time periods and numbers

    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
     ÑģенÑĤ
    -0.26
     Kardash
    -0.25
     )↵↵↵↵↵↵↵↵
    -0.23
     verschill
    -0.21
     informatie
    -0.21
     resultMap
    -0.21
     Köln
    -0.21
    3
    -0.20
    	GLuint
    -0.19
    æĸĩåĮĸåĪĽæĦı
    -0.19
    POSITIVE LOGITS
     rekl
    0.30
    jej
    0.27
    ðŁ¤Ķ
    0.26
    ðŁĻĤ
    0.26
    kke
    0.25
    ucz
    0.24
    æį¢åı¥è¯Ŀ
    0.24
    ðŁĺĦ
    0.24
    ðŁĺģ
    0.24
    :normal
    0.23
    Activations Density 7.691%

    No Known Activations