© 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. 152
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    ãİİ
    -0.33
    åŀ§
    -0.24
    =<?=
    -0.23
    åħ«å¤§ä»¥æĿ¥
    -0.23
    ='../
    -0.23
    =<?=$
    -0.23
    =".$_
    -0.23
    ,
    -0.22
    écoute
    -0.22
    â½ī
    -0.21
    POSITIVE LOGITS
    个交æĺĵ
    0.38
    DMETHOD
    0.32
     burge
    0.31
    åİĨåı²æĸ°
    0.30
     reluct
    0.28
    ä»ħ代表
    0.28
     HeaderComponent
    0.28
     sovere
    0.27
    å¹´ä¹ĭä¹ħ
    0.27
    âĸ½
    0.27
    Activations Density 1.937%

    No Known Activations