© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25178
    Prev
    Next
    INDEX
    Explanations

    design and engineering contexts

    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
    笨
    -0.09
    رÙĪب
    -0.07
     videoc
    -0.07
    arness
    -0.07
    hurt
    -0.07
    缸åħ³éĺħ读
    -0.07
    regar
    -0.07
    átil
    -0.07
    że
    -0.07
    nade
    -0.07
    POSITIVE LOGITS
    åĽ¾çº¸
    0.11
    /engine
    0.11
    /design
    0.10
    ä¸İ设计
    0.09
     drawings
    0.08
     engineers
    0.08
    å·¥ç¨ĭå¸Ī
    0.08
    å°Ķå¾·
    0.07
     заказ
    0.07
     design
    0.07
    Activations Density 0.028%

    No Known Activations