© 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. 1203
    Prev
    Next
    INDEX
    Explanations

    approximately

    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
    withErrors
    -0.23
    ;display
    -0.22
    ÎĪ
    -0.21
    ãĥªãĥķãĤ©ãĥ¼ãĥł
    -0.21
    PropTypes
    -0.21
    é«ĺé¢Ŀ
    -0.20
    诸
    -0.20
    Ͼ
    -0.20
    é«ĺä»·
    -0.20
    пÑĥбли
    -0.20
    POSITIVE LOGITS
    约为
    0.34
    åĪĨåĪ«ä¸º
    0.31
    大约
    0.28
    ï¼ł
    0.28
    é«ĺè¾¾
    0.26
    å¹³åĿĩ
    0.26
    æŶéĹ´ä¸º
    0.26
     ÑģоÑģÑĤавлÑıеÑĤ
    0.25
    %)↵↵
    0.24
     approximately
    0.24
    Activations Density 3.305%

    No Known Activations