© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19479
    Prev
    Next
    INDEX
    Explanations

    Decided July 19, 1985" - The token "be" is present before "Decided".2bBJi9eZPxfU/hgglFh3SMDM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
    åħ´
    -0.07
     Ing
    -0.07
    æł·çļĦ
    -0.06
     impres
    -0.06
    знаÑĩ
    -0.06
    æĻ®
    -0.06
    çļĦä¸į
    -0.06
    å®¢åľº
    -0.06
     Perman
    -0.05
    Syntax
    -0.05
    POSITIVE LOGITS
    å·²ç»ıè¶ħè¿ĩ
    0.05
    ä»Ļä¾ł
    0.05
     graceful
    0.05
    éĩ
    0.05
    æİĸ
    0.05
     ered
    0.05
     Reich
    0.05
    ủng
    0.05
     verl
    0.05
     permitted
    0.05
    Activations Density 0.002%

    No Known Activations