© 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. 19705
    Prev
    Next
    INDEX
    Explanations

    computational knowledge engine

    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
    andır
    -0.07
    æł·
    -0.06
    enov
    -0.06
    بارÙĩ
    -0.06
    ä½ľä¸ºä¸ŃåĽ½
    -0.05
    âĢ¦âĢ¦ãĢĤ
    -0.05
    æĹ
    -0.05
    åİŁæĺ¯
    -0.05
     ÑħоÑĤÑĮ
    -0.05
    upakan
    -0.05
    POSITIVE LOGITS
    æĺ¯éĿł
    0.06
    çłļ
    0.06
    èĢĮå®ļ
    0.05
    pra
    0.05
    ανά
    0.05
     b
    0.05
     Nam
    0.05
    ials
    0.05
     B
    0.05
     judge
    0.05
    Activations Density 0.103%

    No Known Activations