© 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. 1104
    Prev
    Next
    INDEX
    Explanations

    list or array

    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
     enthus
    -0.25
     KeyValuePair
    -0.24
    åıĪ好åıĪ
    -0.24
    GraphNode
    -0.23
    娣
    -0.23
    éĴ£
    -0.22
    ä¸ī大éĺ¶æ®µ
    -0.22
     NotImplementedException
    -0.22
     carbohydr
    -0.21
    æĻĹ
    -0.21
    POSITIVE LOGITS
     list
    0.63
    åĪĹ表
    0.47
    list
    0.47
    åIJįåįķ
    0.46
     List
    0.46
    .list
    0.40
    (list
    0.37
    List
    0.37
    	list
    0.36
    -list
    0.35
    Activations Density 4.912%

    No Known Activations