© 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. 19593
    Prev
    Next
    INDEX
    Explanations

    an or a followed by technical term

    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
    大åĪ©
    -0.06
    çľ¼éĩĮ
    -0.06
    ezu
    -0.06
    eries
    -0.06
    åĺ´éĩĮ
    -0.05
    åIJijçĿĢ
    -0.05
    Corp
    -0.05
     variety
    -0.05
    æŁIJ天
    -0.05
    оÑĢе
    -0.05
    POSITIVE LOGITS
     easier
    0.06
    æĺĵ
    0.06
    prem
    0.06
    æĪĸä¸İ
    0.06
    åħ·ä½ĵ
    0.05
    ragen
    0.05
    èİİ
    0.05
    odo
    0.05
    åķ
    0.05
    æĦļ
    0.05
    Activations Density 0.030%

    No Known Activations