© 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. 11241
    Prev
    Next
    INDEX
    Explanations

    Patent numbers and journal references

    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
    èĥ¡éĶ¦æ¶Ľ
    -0.13
    奥巴马
    -0.12
     Sarkozy
    -0.10
     DVDs
    -0.10
     Obama
    -0.10
    éĢļè¿ĩç½ij绾
    -0.10
    æ¬§çĽŁ
    -0.09
    Obama
    -0.09
     Putin
    -0.09
     Katrina
    -0.09
    POSITIVE LOGITS
     USSR
    0.11
     Telegram
    0.08
     telegram
    0.08
    ä¸Ģä¹Ŀ
    0.08
    çĶµè®¯
    0.08
     Ð¡Ð¡Ð¡Ðł
    0.08
    æĸ°ä¸ŃåĽ½
    0.07
     Soviet
    0.07
    æĺŃåĴĮ
    0.07
     fasc
    0.07
    Activations Density 0.654%

    No Known Activations