© 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. 17891
    Prev
    Next
    INDEX
    Explanations

    Python list and dictionary syntax

    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
    oh
    -0.07
    æĹłéĻIJ
    -0.07
    è£
    -0.07
    ׼×Ļ×Ŀ
    -0.06
     ÅĽci
    -0.06
    ock
    -0.06
    æĢ»æ¯Ķ
    -0.06
    åĨ³å®ļçļĦ
    -0.06
    两项
    -0.06
     tov
    -0.06
    POSITIVE LOGITS
    ordan
    0.07
    å¾·åįİ
    0.07
    _hpp
    0.07
    éĺĸ家
    0.07
    _HIDDEN
    0.07
    _strerror
    0.07
    _KP
    0.07
    arer
    0.07
    æĴ®
    0.07
    letcher
    0.07
    Activations Density 0.040%

    No Known Activations