© 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. 33043
    Prev
    Next
    INDEX
    Explanations

    In [field of study]

    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
    clipse
    -0.07
    ekh
    -0.07
    åk
    -0.07
    ÙĪدÙĩ
    -0.07
    latin
    -0.06
    æļ´åĬĽ
    -0.06
    éĢıæ°´
    -0.06
    ifr
    -0.06
     Nuclear
    -0.06
     unread
    -0.06
    POSITIVE LOGITS
     nutshell
    0.07
     ...,
    0.07
    enna
    0.07
    æŁIJç§įæĦıä¹īä¸Ĭ
    0.07
    (/^\
    0.07
    ...,
    0.07
    çİ°å®ŀçĶŁæ´»ä¸Ń
    0.06
    entic
    0.06
    quir
    0.06
    اربة
    0.06
    Activations Density 0.095%

    No Known Activations