© 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. 2006
    Prev
    Next
    INDEX
    Explanations

    duration of 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
     ninete
    -0.23
    ä¸ī大éĺ¶æ®µ
    -0.23
     neckline
    -0.22
     scaleX
    -0.21
    åģĪ
    -0.21
     "('
    -0.20
    éĩįè¦ģ举æݪ
    -0.20
     germany
    -0.20
     sigu
    -0.20
    ä¸Ģéģĵ
    -0.19
    POSITIVE LOGITS
     time
    0.29
    æľĢéķ¿
    0.28
     months
    0.27
    对åħ¶çľŁå®ŀ
    0.27
     period
    0.26
     days
    0.26
    -With
    0.26
    æŶéĹ´
    0.25
     elapsed
    0.25
     duration
    0.24
    Activations Density 1.775%

    No Known Activations