© 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. 32653
    Prev
    Next
    INDEX
    Explanations

    changing state or position

    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°ĨæѤ
    -0.08
     Alone
    -0.07
    å°Ĩå®ĥ
    -0.07
    ebre
    -0.07
    å°Ĩè¿Ļ
    -0.07
    交æīĭ
    -0.07
    åı¬
    -0.07
    tta
    -0.07
    è¿ĻæĬĬ
    -0.07
    åĭ¢
    -0.07
    POSITIVE LOGITS
     whenever
    0.12
    æ¯ı次
    0.10
    Whenever
    0.10
    å¹¶æł¹æį®
    0.09
    enever
    0.09
     progressively
    0.09
     dần
    0.09
     successive
    0.09
    ä¸Ģ次次
    0.09
     each
    0.09
    Activations Density 0.169%

    No Known Activations