© 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. 723
    Prev
    Next
    INDEX
    Explanations

    +

    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
    :
    -0.24
    -
    -0.23
    uez
    -0.20
    ↵
    -0.20
    [
    -0.20
    \n
    -0.20
    .
    -0.19
    Nguá»ĵn
    -0.19
    ucker
    -0.19
    ä¸įä½Ĩ
    -0.18
    POSITIVE LOGITS
    æĢ»èĢĮè¨Ģ
    0.28
     (*)(
    0.28
    :'.$
    0.26
    .FindGameObjectWithTag
    0.25
    urovision
    0.25
     ãĥĪãĥ©ãĥĥãĤ¯
    0.24
    (*)(
    0.24
    antro
    0.24
    UrlParser
    0.24
     embod
    0.24
    Activations Density 0.330%

    No Known Activations