© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3664
    Prev
    Next
    INDEX
    Explanations

    code and technical 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
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.27
     embod
    -0.24
    ("<?
    -0.23
    ////////////////////////////////////////////////////////////////////////////////↵↵
    -0.23
     MatSnackBar
    -0.23
     PureComponent
    -0.23
     Casinos
    -0.22
     setFrame
    -0.22
     Incontri
    -0.22
    ughs
    -0.22
    POSITIVE LOGITS
    EFAULT
    0.24
     \`
    0.19
    åĢľ
    0.19
    çļĦç¼ĺ
    0.19
     sidel
    0.19
     between
    0.19
    主æĿĥ
    0.19
     apologise
    0.18
    ï¼ģ↵↵↵↵
    0.18
    çļĦé£İéĻ©
    0.18
    Activations Density 0.001%

    No Known Activations