© 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. 1447
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    ĵĺ
    -0.28
    nze
    -0.28
    ">ÃĹ</
    -0.27
    âĦī
    -0.27
    $LANG
    -0.25
    Serviço
    -0.25
    nesty
    -0.24
    ToSelector
    -0.24
    åĨ°æ·ĩ
    -0.24
    FunctionFlags
    -0.24
    POSITIVE LOGITS
    並å°ĩ
    0.22
    ottenham
    0.20
     paramMap
    0.20
    y
    0.19
    P
    0.19
    éĴ¯
    0.19
     therap
    0.18
    R
    0.18
     UITextView
    0.18
    æĺİæĻº
    0.18
    Activations Density 4.410%

    No Known Activations