© 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. 1199
    Prev
    Next
    INDEX
    Explanations

    code

    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
    -sama
    -0.22
    éļ¾æĢª
    -0.21
    å°±ç»Ļ大家
    -0.20
    åĸı
    -0.19
     walmart
    -0.19
    pcodes
    -0.19
    èIJľ
    -0.19
    raquo
    -0.19
    fung
    -0.18
    主è¦ģéĽĨä¸Ń
    -0.18
    POSITIVE LOGITS
     foo
    0.30
    è¿Ļ个èģĮä¸ļ
    0.28
     some
    0.27
     something
    0.25
     another
    0.25
     Ñģдела
    0.24
    some
    0.24
    æĥ³äºĨæĥ³
    0.24
     Some
    0.23
    Some
    0.23
    Activations Density 3.694%

    No Known Activations