© 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. 2029
    Prev
    Next
    INDEX
    Explanations

    UI layout components

    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
     gridColumn
    -0.35
     Playoff
    -0.29
    scrollTop
    -0.28
    popover
    -0.27
     setBackgroundColor
    -0.27
    fillType
    -0.27
     addButton
    -0.27
    TransparentColor
    -0.27
    .labelX
    -0.26
     tbsp
    -0.25
    POSITIVE LOGITS
    éĥ¨åī¯
    0.28
     (;;
    0.25
    åľ¨è¿ĩ渡
    0.24
    ä½Ĩä¸įéĻIJ
    0.24
    .Selenium
    0.24
    _Texture
    0.24
    :"#
    0.23
    ä¸Ģèĩ´å¥½è¯Ħ
    0.22
    WITHOUT
    0.22
    ADX
    0.22
    Activations Density 5.233%

    No Known Activations