© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52136
    Prev
    Next
    INDEX
    Explanations

    in spite of everyone playing

    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
    Negative Logits
    _SECURE
    -0.09
    Embed
    -0.08
    夫妻俩
    -0.08
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.08
    icky
    -0.08
    åIJĥä¸ĢäºĽ
    -0.07
    truct
    -0.07
    hdr
    -0.07
    /pi
    -0.07
    æľīçĶŁ
    -0.07
    POSITIVE LOGITS
     CPC
    0.06
    éĥ¨åĴĮ
    0.06
     over
    0.06
    indi
    0.06
    è¿ĩ
    0.06
    åĩ»
    0.06
    ä¸įå¼Ģ
    0.06
     Roos
    0.06
    pp
    0.06
    æĢĿæĥ³åĴĮè¡ĮåĬ¨
    0.06
    Activations Density 0.030%

    No Known Activations