© 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. 612
    Prev
    Next
    INDEX
    Explanations

    math 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
    cassert
    -0.21
    cstdint
    -0.21
    strncmp
    -0.20
    纲
    -0.19
    Ùħصر
    -0.19
     Ä°zmir
    -0.18
    å°ĸ
    -0.18
    ator
    -0.18
    æĻ®éģį
    -0.18
    StackNavigator
    -0.18
    POSITIVE LOGITS
    *pow
    0.27
    ."&
    0.25
    ogui
    0.25
    *Math
    0.25
    .MM
    0.23
    tingham
    0.23
    âĦī
    0.23
    ":[{↵
    0.23
    ::.
    0.23
    ä¹Įåħĭ
    0.22
    Activations Density 0.499%

    No Known Activations