© 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. 45641
    Prev
    Next
    INDEX
    Explanations

    structure factor, influence function

    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
    ationen
    -0.08
    ogia
    -0.08
    è¿ĻæĹłçĸij
    -0.07
    iations
    -0.07
    åIJĮæŶè¿ĺ
    -0.07
    åĮĸåĴĮ
    -0.06
    åįĬå±±
    -0.06
    éĥ¨ãģ®
    -0.06
     Handy
    -0.06
    æĦıçļĦ
    -0.06
    POSITIVE LOGITS
    /release
    0.07
    ridge
    0.07
    olume
    0.07
    åĽłåŃIJ
    0.07
    eht
    0.07
    /security
    0.07
    å§Ķåijĺä¼ļå§Ķåijĺ
    0.07
    tensor
    0.06
    çłģ
    0.06
    èįł
    0.06
    Activations Density 0.163%

    No Known Activations