© 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. 28490
    Prev
    Next
    INDEX
    Explanations

    places or pursuits

    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
    举举
    -0.08
    å°¤åħ¶æĺ¯åľ¨
    -0.08
     presumably
    -0.07
    èĢħä¹Ł
    -0.07
    åıĬ以ä¸ĭ
    -0.07
    å°¤åħ¶æĺ¯
    -0.07
    对äºİè¿ĻäºĽ
    -0.07
    åģļ好äºĭ
    -0.07
    åıĬ个人
    -0.07
    akter
    -0.07
    POSITIVE LOGITS
    æŁIJ个
    0.12
    æŁIJåĢĭ
    0.12
    æŁIJ
    0.10
    åıĪå¦Ĥ
    0.10
    ãģłãģ£ãģŁãĤĬ
    0.09
    æĬķèµĦæĪĸ
    0.09
    åıĪæĪĸèĢħ
    0.09
    ãģ¨ãģĭ
    0.09
    åĽ¾çīĩæĪĸ
    0.09
    æŁIJä¸Ģ个
    0.08
    Activations Density 0.094%

    No Known Activations