© 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. 19097
    Prev
    Next
    INDEX
    Explanations

    cell injury, processing, vehicle, join

    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
    尼迪
    -0.09
    æĢ»æİĴåIJį
    -0.09
    æĪIJ为ä¸ĢåIJį
    -0.08
    èĢĮéĻį
    -0.08
    çļĦèĥĮåIJİ
    -0.07
    çļĦæıIJé«ĺ
    -0.07
    æ´»åĬ¨ç»ĵæĿŁåIJİ
    -0.07
    人çļĦçĶŁæ´»
    -0.07
    æ°´éĩĮ
    -0.07
    anan
    -0.07
    POSITIVE LOGITS
    æľ¬èº«çļĦ
    0.11
    åıĬåħ¶
    0.09
    èĩªèº«çļĦ
    0.09
    æĪĸåħ¶
    0.09
    çī¹æľīçļĦ
    0.09
    åĽł
    0.08
    çļĦé«ĺ
    0.08
    åĽºæľīçļĦ
    0.08
    åı£ä¸ŃçļĦ
    0.08
    æĮģãģ¤
    0.07
    Activations Density 0.014%

    No Known Activations