© 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. 45733
    Prev
    Next
    INDEX
    Explanations

    increase or strengthen

    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
    大äºĭ
    -0.07
    iros
    -0.07
    OrDefault
    -0.06
     superiority
    -0.06
    èĬ±èIJ½
    -0.06
    çĽ¸ä¼¼æĸĩçĮ®
    -0.06
    æľī个
    -0.06
    çĺŁ
    -0.06
    å§ĭèĩ³ç»Ī
    -0.06
    ä¸įæĸŃæİ¨è¿Ľ
    -0.06
    POSITIVE LOGITS
    äºĨ对
    0.14
    åĴĮå®ĮåĸĦ
    0.11
    ä¸ĢåĢį
    0.10
    åĴĮæĶ¹åĸĦ
    0.10
    /remove
    0.09
    äºĨæĮĩ
    0.09
    åĴĮæıIJé«ĺ
    0.09
    äºĨåĩłåĪĨ
    0.09
    åĴĮä¼ĺåĮĸ
    0.08
    -than
    0.08
    Activations Density 0.066%

    No Known Activations