© 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. 603
    Prev
    Next
    INDEX
    Explanations

    LaTeX symbols

    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
    ">ÃĹ</
    -0.35
    ĵĺ
    -0.24
    loquent
    -0.24
    æĵ¤
    -0.24
    odzi
    -0.24
    \">"
    -0.24
    /Runtime
    -0.23
    :CGRect
    -0.23
    perienced
    -0.23
    .AutoComplete
    -0.23
    POSITIVE LOGITS
    @js
    0.25
     Sized
    0.24
     Erotic
    0.24
    longleftrightarrow
    0.22
     siti
    0.22
     unfavor
    0.22
     vagy
    0.22
     testim
    0.21
     ASUS
    0.21
    IFICATIONS
    0.21
    Activations Density 0.086%

    No Known Activations