© 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. 1044
    Prev
    Next
    INDEX
    Explanations

    license text

    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
    çļĦ带é¢Ĩ
    -0.27
    äºĨ好å¤ļ
    -0.24
     NRA
    -0.22
     ofApp
    -0.22
    读åIJİæĦŁ
    -0.22
    å§Ķç»Ħç»ĩ
    -0.22
    åĺ£
    -0.22
     franç
    -0.21
     Seks
    -0.21
    åĹIJ
    -0.20
    POSITIVE LOGITS
    æį¢åı¥è¯Ŀ
    0.28
     ((__
    0.22
    -animate
    0.21
    arcer
    0.20
    ://%
    0.20
     Unsure
    0.19
    /umd
    0.19
    ynet
    0.19
    /mit
    0.19
    èѬå¦Ĥ
    0.19
    Activations Density 2.563%

    No Known Activations