© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47601
    Prev
    Next
    INDEX
    Explanations

    death, death rate, death of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ezza
    -0.09
    mÃ¤ÃŁig
    -0.09
    ever
    -0.09
    наÑĩ
    -0.08
    رÙĬÙĨ
    -0.08
    пли
    -0.08
    ignKey
    -0.07
    णà¥Ģ
    -0.07
    سازÛĮ
    -0.07
    itional
    -0.07
    POSITIVE LOGITS
    æİīçļĦ
    0.09
    æ®Ĩå°½
    0.08
    สà¸Ļิà¸Ĺ
    0.08
    çİĩé«ĺ
    0.08
    身亡
    0.08
    -death
    0.07
    /de
    0.07
     Äijuá»iji
    0.07
    æĥ¨éĩį
    0.07
    wards
    0.07
    Activations Density 0.087%

    No Known Activations