© 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. 1989
    Prev
    Next
    INDEX
    Explanations

    strange characters

    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
    游æĪıæĵįä½ľ
    -0.25
    äºĨ好å¤ļ
    -0.23
    èįŁ
    -0.21
    ><?=$
    -0.21
    Descriptors
    -0.20
    çļĦéģĵçIJĨ
    -0.20
    ’d
    -0.20
    "path
    -0.20
    äºĨä¸Ģä¼ļ
    -0.20
    ActionCreators
    -0.19
    POSITIVE LOGITS
    è¯įæĿ¡
    0.28
    注æĺİæĿ¥æºIJ
    0.23
    ÅŁÄ±k
    0.23
    ľëł¥
    0.23
    []{↵
    0.23
     lié
    0.22
     showc
    0.22
     Barang
    0.22
     kut
    0.22
     èĩªåĬ¨çĶŁæĪIJ
    0.22
    Activations Density 1.219%

    No Known Activations