© 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. 1670
    Prev
    Next
    INDEX
    Explanations

    links ending in .com or .app

    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
    å½¼æѤ
    -0.07
    striction
    -0.07
    assen
    -0.07
    ject
    -0.07
    毡
    -0.07
    æĸ°ç¤¾
    -0.07
    wart
    -0.06
    ykl
    -0.06
    åĪ¤
    -0.06
    æģ¶
    -0.06
    POSITIVE LOGITS
    imonial
    0.08
    åŃIJéĩĮ
    0.08
    åĿĢ
    0.08
    åŃIJåľ¨
    0.08
    åŃIJä¸Ĭ
    0.08
    sWith
    0.07
    åŃIJçļĦ
    0.07
    欣欣
    0.07
    åŃIJåĴĮ
    0.07
     fours
    0.07
    Activations Density 0.026%

    No Known Activations