© 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. 45827
    Prev
    Next
    INDEX
    Explanations

    include header files

    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
     سÙĦÙħ
    -0.08
    /csv
    -0.08
    è¿ĻäºĽæķ°æį®
    -0.07
    æ°¸åĴĮ
    -0.07
    /items
    -0.07
    表çİ°å¾Ĺ
    -0.07
    ä¹Ŀ寨
    -0.07
     Colomb
    -0.06
    indel
    -0.06
    esian
    -0.06
    POSITIVE LOGITS
     snippets
    0.07
    ught
    0.07
     directives
    0.07
    خش
    0.07
    第ä¸Ģç¯ĩ
    0.07
    intosh
    0.07
     definitions
    0.07
    èIJ½å®ŀ
    0.07
    fox
    0.07
    Arduino
    0.07
    Activations Density 0.344%

    No Known Activations