© 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. 9159
    Prev
    Next
    INDEX
    Explanations

    node, high, mium, pattern, km, Maui

    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
    å¸Ĩ
    -0.06
    ÑĪов
    -0.06
     considering
    -0.06
    igni
    -0.06
    Winner
    -0.06
    tti
    -0.06
    (com
    -0.06
    ë
    -0.06
    \Annotation
    -0.06
     Gem
    -0.06
    POSITIVE LOGITS
    æīĢ带æĿ¥çļĦ
    0.12
    导èĩ´
    0.09
    带æĿ¥çļĦ
    0.09
    èĩ´ä½¿
    0.09
    ä¼ļ带æĿ¥
    0.09
    带ç»ĻæĪij们
    0.09
    带æĿ¥
    0.08
    å°İèĩ´
    0.08
    æīĢ产çĶŁçļĦ
    0.08
    帶ä¾Ĩ
    0.08
    Activations Density 0.007%

    No Known Activations