© 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. 44442
    Prev
    Next
    INDEX
    Explanations

    shape memory alloy, responsive polymer, variable devices

    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
    æī«
    -0.08
    ä¸īæĹ¥
    -0.07
     estimate
    -0.07
     Estimates
    -0.07
     estimates
    -0.07
     swept
    -0.07
    ä¼°ç®Ĺ
    -0.06
     pitched
    -0.06
    估计
    -0.06
    åŁºæľ¬
    -0.06
    POSITIVE LOGITS
    -trigger
    0.10
    trigger
    0.10
    éļ±èĹı
    0.09
    éļIJèĹı
    0.09
    触åıij
    0.09
     triggered
    0.09
     activated
    0.09
     Trigger
    0.09
    åıĺèī²
    0.09
    	trigger
    0.08
    Activations Density 0.114%

    No Known Activations