© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15836
    Prev
    Next
    INDEX
    Explanations

    metal-assisted catalyzed etching

    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
    .gz
    -0.07
    æıĴä¸Ĭ
    -0.07
    æıĴ
    -0.07
     Seeder
    -0.07
    è¡
    -0.07
    æį»
    -0.07
    æĬ¼
    -0.07
    æłĵ
    -0.07
    éļıå¤Ħ
    -0.07
    èIJ½åľ°
    -0.07
    POSITIVE LOGITS
    èļĢ
    0.10
    èħIJèļĢ
    0.09
    chants
    0.09
    ä¾µèļĢ
    0.09
    åİ»éĻ¤
    0.09
     tẩy
    0.08
    éĽķåĪ»
    0.08
     agents
    0.07
    unes
    0.07
     disproportionate
    0.07
    Activations Density 0.039%

    No Known Activations