© 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. 55604
    Prev
    Next
    INDEX
    Explanations

    increase or duration

    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¦ĤæĦ¿
    -0.07
    红å°ĺ
    -0.07
    inea
    -0.07
    ç³Ĭ
    -0.07
     chaining
    -0.06
    åįİå°Ķ
    -0.06
    uchen
    -0.06
    ä¸įèĻļ
    -0.06
    ampion
    -0.06
     fel
    -0.06
    POSITIVE LOGITS
    åĩıæ³ķ
    0.12
    åĩıè´Ł
    0.11
    åĩı
    0.10
    éģ¿å¼Ģ
    0.10
    :disable
    0.09
    åī©ä¸ĭ
    0.09
    æ¸Ľ
    0.09
     subtraction
    0.09
    åĩıåİ»
    0.09
     subtract
    0.09
    Activations Density 0.073%

    No Known Activations