© 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. 39365
    Prev
    Next
    INDEX
    Explanations

    legal and technical code

    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
     ê²½ìļ°ìĹIJëĬĶ
    -0.08
    åħħ满äºĨ
    -0.07
    éļıçĿĢæŶéĹ´çļĦæݨ移
    -0.07
    åľ¨ä¸įåIJĮçļĦ
    -0.07
    çľĭä¸Ģçľĭ
    -0.07
    æĪĸèĢħ说
    -0.07
    ï¼Į
    -0.07
    ä»Ķç»Ĩåľ°
    -0.07
    æĪĸèĢħæĺ¯
    -0.07
    以åıĬ
    -0.07
    POSITIVE LOGITS
    åĽłç´łå½±åĵį
    0.10
    æľīæѤ
    0.10
    åĨħ容æľī
    0.10
    æĿIJæĸĻåıĬ
    0.09
    ä¸īæĸ¹éĿ¢
    0.09
    é§ħå¾ĴæŃ©
    0.09
    çİĩè¾¾
    0.09
    æīĢ以ä»ĸ们
    0.09
    ighest
    0.09
    æīįåı¯
    0.09
    Activations Density 0.019%

    No Known Activations