© 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. 1029
    Prev
    Next
    INDEX
    Explanations

    errors detected

    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
    traî
    -0.24
    对åħ¶çľŁå®ŀ
    -0.23
    /fontawesome
    -0.22
    黥
    -0.22
    )))),
    -0.22
    .Magenta
    -0.22
    æĢĬ
    -0.22
    -Cs
    -0.22
     AssemblyTitle
    -0.21
    å¹´ä¹ĭä¹ħ
    -0.21
    POSITIVE LOGITS
     detected
    0.27
     cannot
    0.27
     attempted
    0.25
    ç»ıæŁ¥
    0.24
    æĹłæ³ķ
    0.24
    æŃ£åľ¨
    0.23
     condol
    0.23
     requested
    0.23
    Cannot
    0.22
     beneficiation
    0.22
    Activations Density 1.642%

    No Known Activations