© 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. 1665
    Prev
    Next
    INDEX
    Explanations

    academic fields

    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
    读åIJİæĦŁ
    -0.26
     newArr
    -0.23
    'user
    -0.22
     resembl
    -0.22
    anoia
    -0.22
     (;;
    -0.22
    xDE
    -0.22
    ÙĤدÙĬر
    -0.22
    ovenant
    -0.21
    (',',$
    -0.21
    POSITIVE LOGITS
    -related
    0.29
    é¢ĨåŁŁ
    0.28
     sciences
    0.27
    é¢ĨåŁŁçļĦ
    0.27
    ç±»
    0.26
    -oriented
    0.26
     PureComponent
    0.25
    çĶ¨åĵģ
    0.24
    -minded
    0.24
    æĸ¹éĿ¢çļĦ
    0.24
    Activations Density 7.089%

    No Known Activations