© 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. 172
    Prev
    Next
    INDEX
    Explanations

    code and conversations

    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
    äºĨ好å¤ļ
    -0.27
    äºĨ好åĩł
    -0.26
    usterity
    -0.26
    äºĨåįĬ天
    -0.23
    éĹ»è¨Ģ
    -0.23
    å®Ŀå¦Ī
    -0.21
     TMPro
    -0.20
    çļĦç¼ĺ
    -0.20
    åIJĦå¼ıåIJĦæł·
    -0.19
    äºĨè¿ĩæĿ¥
    -0.19
    POSITIVE LOGITS
    æľĢåIJİ
    0.28
    éĻĦ
    0.27
    lke
    0.26
     fkk
    0.25
     finally
    0.24
    anax
    0.23
    à¥IJ
    0.23
    :".$
    0.23
    æĢ»ä¹ĭ
    0.23
    rô
    0.23
    Activations Density 1.578%

    No Known Activations