© 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. 47420
    Prev
    Next
    INDEX
    Explanations

    compatible with

    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
    th
    -0.07
    nick
    -0.06
     dér
    -0.06
    å¾ĪæĹ©
    -0.06
     dissect
    -0.06
    é¢ĩ
    -0.05
    å±ģèĤ¡
    -0.05
    æµģ浪
    -0.05
    ä¿Ĺ
    -0.05
    çªij
    -0.05
    POSITIVE LOGITS
    æĽ´éĢĤåIJĪ
    0.14
    æĽ´ç¬¦åIJĪ
    0.13
    æĸ°çļĦ
    0.11
    åıĺå¾ĹæĽ´
    0.11
    åıĺå¾ĹæĽ´åĬł
    0.11
    æĽ´åħ·
    0.10
    æľīäºĨæĸ°çļĦ
    0.10
    ä»¥æĽ´
    0.10
    æľīæĽ´å¥½çļĦ
    0.10
    æĽ´æľīåĪ©äºİ
    0.10
    Activations Density 0.273%

    No Known Activations