© 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. 139
    Prev
    Next
    INDEX
    Explanations

    advisable

    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
    éĥ¨åī¯
    -0.26
     ePub
    -0.25
    é»ijæģ¶
    -0.23
    åħ³äºİæĪij们
    -0.23
    äºĨ好å¤ļ
    -0.22
    imagenes
    -0.22
    åıĪ好åıĪå¿«
    -0.22
    éĻ¢åī¯éĻ¢éķ¿
    -0.22
    âĬĬ
    -0.21
    æīĢæıIJä¾Ľ
    -0.21
    POSITIVE LOGITS
    建议
    0.44
    åĬ¡å¿ħ
    0.42
    ä¸Ģå®ļè¦ģ
    0.39
    ä¸įè¦ģ
    0.36
    å°½éĩı
    0.35
    åįĥä¸ĩä¸įè¦ģ
    0.34
    ä½łåºĶ该
    0.33
    æľĢ好
    0.32
     should
    0.32
     advisable
    0.32
    Activations Density 2.799%

    No Known Activations