© 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. 19520
    Prev
    Next
    INDEX
    Explanations

    years passed since

    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
    anak
    -0.07
    mittelt
    -0.07
    anto
    -0.06
    çĶ³æĺİ
    -0.06
    tics
    -0.06
    ieux
    -0.06
    è¶Ĭæĺ¯
    -0.06
    ä¸įèĥ½æ»¡è¶³
    -0.06
    æĿ¥è¶Ĭ
    -0.06
    utes
    -0.06
    POSITIVE LOGITS
    ž
    0.05
    bero
    0.05
    ff
    0.05
    ç¹ģ
    0.05
    æĪij
    0.05
     asleep
    0.05
    amp
    0.05
    ÙĨØ©
    0.05
    åŃĺ
    0.05
     stabile
    0.05
    Activations Density 0.003%

    No Known Activations