© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1698
    Prev
    Next
    INDEX
    Explanations

    code, programming 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
    движ
    -0.19
    Für
    -0.19
    راÙħ
    -0.18
    .recycle
    -0.18
     Gos
    -0.18
    æģ¬
    -0.18
     bisc
    -0.17
    :;"
    -0.17
    SingleOrDefault
    -0.17
    æĩ¦
    -0.17
    POSITIVE LOGITS
    antino
    0.26
    女æĢ§æľĭåıĭ
    0.25
     Redistributions
    0.24
    InputChange
    0.24
    åĵĪåĵĪåĵĪåĵĪ
    0.23
    å´Ł
    0.22
     ìłĦíĺĢ
    0.22
     Ãĸn
    0.21
    strcasecmp
    0.21
    WEBPACK
    0.21
    Activations Density 4.035%

    No Known Activations