© 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. 42344
    Prev
    Next
    INDEX
    Explanations

    code contexts

    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
    .TryParse
    -0.08
    桨
    -0.07
    åĿıçļĦ
    -0.07
    æł¹æį®åĽ½å®¶
    -0.07
    åĨħéĥ¨çļĦ
    -0.07
    æĸĮ
    -0.07
    æ§Ľ
    -0.07
    é»Ħç´ł
    -0.07
    ä¼Ļ
    -0.07
    ženÃŃ
    -0.07
    POSITIVE LOGITS
     ↵
    0.08
    luk
    0.07
    åĴĮçĶ°
    0.07
    usza
    0.07
     motivating
    0.06
    åıĪåIJį
    0.06
    æºIJ
    0.06
    Aliases
    0.06
    éros
    0.06
    åıĹéĤĢ
    0.06
    Activations Density 0.011%

    No Known Activations