© 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. 767
    Prev
    Next
    INDEX
    Explanations

    printing, fabrication, editing, installation, repair

    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
    Negative Logits
    å·¡è§Ĩ
    -0.07
    èĩªæĪIJ
    -0.07
    ä¸Ģä½ľ
    -0.07
    elder
    -0.06
    reiro
    -0.06
    ä½łæĢİä¹Ī
    -0.06
    subst
    -0.06
    以身
    -0.06
    å¤ĩ课
    -0.06
     Collector
    -0.06
    POSITIVE LOGITS
     заказ
    0.11
     заказаÑĤÑĮ
    0.11
     request
    0.10
     turnaround
    0.10
    è²»çĶ¨
    0.10
     requested
    0.09
    è´¹çĶ¨
    0.09
    è´¹çĶ¨çĶ±
    0.09
    è´¹çĶ¨çļĦ
    0.09
    å§Ķæīĺ
    0.09
    Activations Density 0.256%

    No Known Activations