© 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. 948
    Prev
    Next
    INDEX
    Explanations

    treatment

    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
     entreprene
    -0.27
     roomId
    -0.25
    çļĦ带é¢Ĩ
    -0.25
    åĦĨ
    -0.23
    è¿Ļ款车
    -0.22
    çļĦç¼ĺ
    -0.22
     foyer
    -0.22
    å®ĺ宣
    -0.21
    æŃ£å¸¸ä½¿çĶ¨
    -0.21
     kol
    -0.21
    POSITIVE LOGITS
     eventdata
    0.28
    å¤įå·¥å¤į
    0.28
    ábado
    0.26
     pund
    0.25
    对åħ¶çľŁå®ŀ
    0.25
    @dynamic
    0.25
    mmo
    0.25
    -lfs
    0.25
    grily
    0.25
    :description
    0.24
    Activations Density 10.760%

    No Known Activations