© 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. 24605
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and claims

    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
    æĸĩæĺİåĬŀ
    -0.07
    åªĴ
    -0.07
    èĩªè§īéģµå®Ī
    -0.06
    èĪ¹ä¸Ĭ
    -0.06
    ilyn
    -0.06
    Ùĩب
    -0.06
    THREAD
    -0.06
    ustry
    -0.06
    å²Ľä¸Ĭ
    -0.06
    å¾ĢçĶŁ
    -0.06
    POSITIVE LOGITS
    è¡ĮæĶ¿è¯ī讼
    0.10
    è¡ĮæĶ¿æľºåħ³
    0.09
    è¡ĮæĶ¿
    0.09
    è¡ĮæĶ¿è¡Į为
    0.08
    ä¸įäºĪåıĹçIJĨ
    0.08
    è´¢æĶ¿èµĦéĩij
    0.08
    æĬķè¯ī
    0.08
     láºŃt
    0.08
    信访
    0.08
    voke
    0.08
    Activations Density 0.057%

    No Known Activations