© 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. 742
    Prev
    Next
    INDEX
    Explanations

    factors

    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
    ;};↵
    -0.22
    :UITableView
    -0.22
    zerbai
    -0.22
    agnost
    -0.21
    çļĦçĶŁåij½
    -0.21
    æĸ°çļĦä¸Ģå¹´
    -0.20
    æİ´
    -0.20
     entire
    -0.19
    getElementsByTagName
    -0.19
    ä¸ĭ次
    -0.19
    POSITIVE LOGITS
     factors
    0.38
    åĽłç´ł
    0.35
     lack
    0.35
    ä»Ģä¹ĪåİŁåĽł
    0.33
     fact
    0.32
     inherent
    0.31
    çŃīåĽłç´ł
    0.30
    çļĦåĽłç´ł
    0.30
     factor
    0.29
     Factors
    0.29
    Activations Density 3.299%

    No Known Activations