© 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. 56608
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms

    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
    _generated
    -0.08
    æīĭåı¯
    -0.07
    è¿ĶãģĹ
    -0.07
    .exports
    -0.07
    èĮģ壮æĪIJéķ¿
    -0.07
    åı¯ä»¥åİ»
    -0.07
    cina
    -0.06
    iek
    -0.06
    iki
    -0.06
    лей
    -0.06
    POSITIVE LOGITS
    缴æİ¥è¿Ľåħ¥
    0.10
    缴æİ¥
    0.09
    缴æİ¥åľ¨
    0.09
    转åĮĸ为
    0.08
    缴æݥ被
    0.08
    缴æİ¥æݥ触
    0.08
    -derived
    0.08
     ì§ģìłij
    0.08
    转åĮĸæĪIJ
    0.08
     Mellon
    0.08
    Activations Density 0.251%

    No Known Activations