© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1385
    Prev
    Next
    INDEX
    Explanations

    time

    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
    æ°´å¹³
    -0.29
    _level
    -0.26
     level
    -0.24
    Level
    -0.24
    -level
    -0.23
     levels
    -0.23
    ãĥ¬ãĥĻãĥ«
    -0.23
     mouseX
    -0.22
    level
    -0.22
    usterity
    -0.22
    POSITIVE LOGITS
     time
    0.38
    æŶéĹ´
    0.35
    éķ¿çŁŃ
    0.33
    æľĢéķ¿
    0.33
     æŶéĹ´
    0.32
    .time
    0.30
    =time
    0.30
    æµģéĢĿ
    0.30
     اÙĦزÙħÙĨ
    0.30
     elapsed
    0.28
    Activations Density 2.985%

    No Known Activations