© 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. 25478
    Prev
    Next
    INDEX
    Explanations

    exclusively, isolated, or both

    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
    å¦ĤèĬ±
    -0.07
    lish
    -0.07
    åħĭåĬĽ
    -0.07
    ifix
    -0.07
    Ð¢ÐŁ
    -0.07
    ç¥ŀä»Ļ
    -0.06
    ESI
    -0.06
    常æľī
    -0.06
    ulasi
    -0.06
    unes
    -0.06
    POSITIVE LOGITS
    æĪĸéĥ¨åĪĨ
    0.09
    åįķä¸ĢçļĦ
    0.08
     либо
    0.08
    æĪĸ以
    0.08
    æĢ§æĪĸ
    0.07
     ëĺIJëĬĶ
    0.07
     íĺ¹ìĿĢ
    0.07
    yonel
    0.07
    æĢ§ä»¥åıĬ
    0.07
    纯粹çļĦ
    0.07
    Activations Density 0.041%

    No Known Activations