© 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. 21469
    Prev
    Next
    INDEX
    Explanations

    scientific observation and measurement

    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
    èĩªæĪij管çIJĨ
    -0.07
    åĨ³å®ļçļĦ
    -0.07
    è¡Įäºij
    -0.07
    nay
    -0.07
    ç»ıæŁ¥
    -0.06
    è¡Ķæİ¥
    -0.06
    积æŀģåºĶ对
    -0.06
    ä¸įè§ī
    -0.06
    好礼
    -0.06
    .Manager
    -0.06
    POSITIVE LOGITS
    åıªèĥ½éĢļè¿ĩ
    0.12
     indirect
    0.10
    struments
    0.10
     indirectly
    0.10
    éĹ´æİ¥
    0.09
     indire
    0.09
     clues
    0.09
     inaccessible
    0.09
     billions
    0.09
    缴æİ¥æĪĸéĹ´æİ¥
    0.09
    Activations Density 0.054%

    No Known Activations