© 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. 98
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è£ħä¿®åħ¬åı¸
    -0.20
    [strlen
    -0.20
     PropertyInfo
    -0.20
    подоб
    -0.20
    iek
    -0.20
    主ä¹īèĢħ
    -0.20
     inf
    -0.19
    habit
    -0.18
    äºĨ解ä¸Ģä¸ĭ
    -0.18
     createContext
    -0.18
    POSITIVE LOGITS
     florida
    0.28
    peare
    0.26
    ystems
    0.24
    +-+-
    0.23
     Dresses
    0.23
     Após
    0.22
    :;↵
    0.22
     Decompiled
    0.22
     porr
    0.22
    ceptar
    0.22
    Activations Density 0.001%

    No Known Activations