© 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. 19417
    Prev
    Next
    INDEX
    Explanations

    code ending quotes

    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
    ç½®äºİ
    -0.06
    ç½®ä¹ĭ
    -0.05
     wont
    -0.05
    ת
    -0.05
    adari
    -0.05
    èµ°å¾Ĺ
    -0.05
    heit
    -0.05
    ãĤĴèµ·ãģĵ
    -0.05
    tre
    -0.05
     hoy
    -0.05
    POSITIVE LOGITS
    iero
    0.06
    çŃīé¢Ĩ导
    0.06
    å¿Ĩ
    0.06
    izzo
    0.05
    irk
    0.05
     Bulls
    0.05
    BrowserRouter
    0.05
    æķĪ
    0.05
    ÃŃsticas
    0.05
     خطÙĬرة
    0.05
    Activations Density 0.019%

    No Known Activations