© 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. 758
    Prev
    Next
    INDEX
    Explanations

    code and licenses

    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
    ä½Ĩæĺ¯å¯¹äºİ
    -0.26
    é¾ĩ
    -0.24
    åĻĺ
    -0.23
    -*-
    -0.23
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.23
     Geschäfts
    -0.23
    窸
    -0.22
     både
    -0.21
    åĴĮ个人
    -0.21
     авгÑĥÑģÑĤ
    -0.20
    POSITIVE LOGITS
    /Dk
    0.31
     indeb
    0.30
     ×Ķ×ķ×ĵ
    0.30
     nostalg
    0.30
     helicopt
    0.29
     vö
    0.29
     libertine
    0.28
     strugg
    0.28
     irresist
    0.28
     incons
    0.27
    Activations Density 0.775%

    No Known Activations