© 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. 1425
    Prev
    Next
    INDEX
    Explanations

    used

    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
    æľĭåıĭ们对
    -0.29
    /vendors
    -0.21
    åĽĽä¸ªæĦıè¯Ĩ
    -0.21
     CONSEQUENTIAL
    -0.20
    æŀ¥
    -0.20
    治好
    -0.20
    æĪķ
    -0.20
    æīįè¡Į
    -0.20
     nomine
    -0.19
    usalem
    -0.19
    POSITIVE LOGITS
    çĶ¨éĢĶ
    0.54
    çĶ¨äºİ
    0.47
    åºĶçĶ¨äºİ
    0.42
     purposes
    0.41
     applications
    0.40
     Used
    0.40
     used
    0.39
    主è¦ģçĶ¨äºİ
    0.38
    Used
    0.38
    çĶ¨æĿ¥
    0.34
    Activations Density 7.560%

    No Known Activations